{ "complete": true, "report": { "bucket": "emo_Astonishment_Surprise", "label": "Intense Astonishment Surprise", "definition": { "id": "emo_Astonishment_Surprise", "category": "emotion", "head": "emo_Astonishment_Surprise", "pole": "high", "label": "Intense Astonishment Surprise", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_astonishment_surprise/full-v2-sealed/sealed-selected", "mission": "emotion_astonishment_surprise", "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": 6.267009663581848, "genuineness": 4.094007096290588, "wer": 0.008686448545319513, "identity": 0.5935249090194702, "voiceclap": -0.03862414427101612, "fitness": 0.8008596357490738, "steering_v2": 0.9609592283116741, "raw_target": 1.8528111766278743, "target_cdf": 0.9609592283116741, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.2807504844665525, "genuineness": 4.082961254119873, "wer": 0.011004399560851174, "identity": 0.5935249090194702, "fitness": 0.807874832327581, "steering_v2": 0.9795041884876379 }, "none": { "n": 50, "ce": 6.2532688426971434, "genuineness": 4.105052938461304, "wer": 0.006368497529787852, "identity": null, "fitness": 0.7938444391705667, "steering_v2": 0.9424142681357104 } } } } ], "selected_wording": { "id": "manual-bedaa97ab879", "general": "Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.", "inline": [ "Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.", "Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.", "Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end." ], "cfg": 3, "recipe": "P05", "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": 3.0 }, "n": 20, "target_z": 2.9687500188896188, "target_raw": 1.9171013116836548, "ce": 6.1127629518508915, "genuineness": 4.184444868564606, "identity": 0.5459338515996933, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.004182276129722595, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 3.021093702438639, "target_raw": 1.9460053980350493, "ce": 6.0583556413650514, "genuineness": 4.184444856643677, "identity": 0.5252109929919243, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.02490513473749161, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.9687500188896188, "target_raw": 1.9171013116836548, "ce": 6.1127629518508915, "genuineness": 4.184444868564606, "identity": 0.5459338515996933, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.004182276129722595, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 2.1562988202191886, "target_raw": 1.4684672452509404, "ce": 6.150689172744751, "genuineness": 4.271054184436798, "identity": 0.528421176970005, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.021694950759410858, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.8210937483134269, "target_raw": 1.2833676174283029, "ce": 6.161014676094055, "genuineness": 4.266033411026001, "identity": 0.5198626644909382, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.030253463238477708, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.7375488485536165, "target_raw": 0.6850361049175262, "ce": 6.181467032432556, "genuineness": 4.358291149139404, "identity": 0.5577588483691216, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.007642720639705658, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.5792236431533012, "target_raw": 0.5976092159748078, "ce": 6.202117967605591, "genuineness": 4.345111465454101, "identity": 0.5562640219926834, "wer": 0.03598211214310286, "valid_fraction": 0.95, "identity_delta": 0.006147894263267517, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.3786376966301352, "target_raw": 0.48684602305293084, "ce": 6.174715781211853, "genuineness": 4.31122088432312, "identity": 0.5699501082301139, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.019833980500698088, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 4.63828113969812, "target_raw": 2.839013344049454, "ce": 5.896523666381836, "genuineness": 3.9472105383872984, "identity": 0.47437505004927516, "wer": 0.025201023391812866, "valid_fraction": 0.95, "identity_delta": -0.07574107768014074, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 3.9585936214831308, "target_raw": 2.4636911392211913, "ce": 6.009508204460144, "genuineness": 4.036644113063812, "identity": 0.4619958661496639, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.08812026157975197, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 3.021093702438639, "target_raw": 1.9460053980350493, "ce": 6.0583556413650514, "genuineness": 4.184444856643677, "identity": 0.5252109929919243, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.02490513473749161, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 2.892578055681846, "target_raw": 1.8750392928719521, "ce": 6.04108030796051, "genuineness": 4.119801652431488, "identity": 0.5002402037382125, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.04987592399120331, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.599218714581965, "target_raw": 1.7130468010902404, "ce": 6.091714882850647, "genuineness": 4.149612784385681, "identity": 0.5118537873029709, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03826234042644501, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 2.1209472269392298, "target_raw": 1.4489461600780487, "ce": 6.099657487869263, "genuineness": 4.239046335220337, "identity": 0.5006139174103736, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04950221031904221, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.9357422076545483, "target_raw": 1.3466762870550155, "ce": 6.106805920600891, "genuineness": 4.229318511486054, "identity": 0.5535511285066604, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.003435000777244568, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.586865249448747, "target_raw": 1.1540270686149596, "ce": 6.160617518424988, "genuineness": 4.283606255054474, "identity": 0.517040166258812, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.033075961470603946, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.5673339883173647, "target_raw": 1.1432419419288635, "ce": 6.1592275381088255, "genuineness": 4.263836824893952, "identity": 0.5100615620613098, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.04005456566810608, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.2213623263072588, "target_raw": 0.9521970227360725, "ce": 6.175907182693481, "genuineness": 4.222414898872375, "identity": 0.5010278493165969, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.04908827841281891, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.0557128898871242, "target_raw": 0.8607257068157196, "ce": 6.176304316520691, "genuineness": 4.350132298469544, "identity": 0.5817058473825455, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.03158971965312958, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.8788574436107107, "target_raw": 0.7630664527416229, "ce": 6.199338054656982, "genuineness": 4.332559370994568, "identity": 0.529991015791893, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.020125111937522887, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.8203125168657308, "target_raw": 0.7307380512356758, "ce": 6.2176062107086185, "genuineness": 4.362056732177734, "identity": 0.5377007499337196, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.012415377795696259, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.754101562247014, "target_raw": 0.6941764831542969, "ce": 6.208074998855591, "genuineness": 4.337580275535584, "identity": 0.5429527640342713, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0071633636951446535, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.5260498053937525, "target_raw": 0.5682467199862004, "ce": 6.168361663818359, "genuineness": 4.295216965675354, "identity": 0.5504528477787971, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0003367200493812561, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.5163818314575402, "target_raw": 0.5629080824553967, "ce": 6.202912282943726, "genuineness": 4.400340628623963, "identity": 0.5568221256136894, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.006705997884273529, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.37692870966202907, "target_raw": 0.48590232357382773, "ce": 6.206883645057678, "genuineness": 4.34573905467987, "identity": 0.5819942802190781, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.03187815248966217, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.28378908046200335, "target_raw": 0.4344707906246185, "ce": 6.197749495506287, "genuineness": 4.316555511951447, "identity": 0.5790759637951851, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.028959836065769195, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.24758300853983464, "target_raw": 0.41447786390781405, "ce": 6.179679942131043, "genuineness": 4.3294213056564335, "identity": 0.5923322305083275, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.04221610277891159, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 4.845312309079927, "target_raw": 2.953335577249527, "ce": 5.862767338752747, "genuineness": 3.8977867364883423, "identity": 0.39802063573151825, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.15209549199789762, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 4.6996092547473385, "target_raw": 2.8728786170482636, "ce": 5.837350797653198, "genuineness": 3.9415621399879455, "identity": 0.3968304440379143, "wer": 0.021052631578947368, "valid_fraction": 0.95, "identity_delta": -0.1532856836915016, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 4.655468609339804, "target_raw": 2.8485042333602903, "ce": 5.956689429283142, "genuineness": 3.918497622013092, "identity": 0.42315860018134116, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": -0.1269575275480747, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 4.043749932537077, "target_raw": 2.5107142984867097, "ce": 6.000572681427002, "genuineness": 4.022836804389954, "identity": 0.4511554865166545, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.09896064121276141, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 3.8296873994802443, "target_raw": 2.3925093591213225, "ce": 6.000175595283508, "genuineness": 4.050765204429626, "identity": 0.4704992452636361, "wer": 0.006066176470588235, "valid_fraction": 1, "identity_delta": -0.07961688246577978, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 3.671484264192148, "target_raw": 2.3051498770713805, "ce": 5.987268710136414, "genuineness": 4.097521674633026, "identity": 0.4870836451649666, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.06303248256444931, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 2.356738272353327, "target_raw": 1.5791495442390442, "ce": 6.127059721946717, "genuineness": 4.200448763370514, "identity": 0.49621704369783404, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.053899084031581876, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.1235351519070743, "target_raw": 0.3459788642823696, "ce": 6.2068836212158205, "genuineness": 4.366450023651123, "identity": 0.5501161277294159, "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": 0.2054687712508209, "target_raw": 0.3912224590778351, "ce": 6.226343178749085, "genuineness": 4.354525578022003, "identity": 0.5004703901708126, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.049645737558603284, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.4995361438279305, "target_raw": 0.5536059245467186, "ce": 6.208869290351868, "genuineness": 4.300865375995636, "identity": 0.5636184766888619, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": 0.013502348959445954, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.21684570921774526, "target_raw": 0.3975047834217548, "ce": 6.168361639976501, "genuineness": 4.319693493843078, "identity": 0.5121734157204628, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03794271200895309, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.2251367117254231, "target_raw": 0.4020830598473549, "ce": 6.257081289291381, "genuineness": 4.31404510974884, "identity": 0.5546397522091866, "wer": 0.008457745153397327, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 2.7873827526772526, "target_raw": 1.8169506388902663, "ce": 6.138417778015136, "genuineness": 4.11766776561737, "identity": 0.5250219690799713, "wer": 0.007492941840767927, "valid_fraction": 1, "identity_delta": -0.02961778312921524, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 2.804023387290719, "target_raw": 1.826139566898346, "ce": 6.15112603187561, "genuineness": 4.169947180747986, "identity": 0.5156369972229004, "wer": 0.006457745153397327, "valid_fraction": 1, "identity_delta": -0.039002754986286164, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 2.7873827526772526, "target_raw": 1.8169506388902663, "ce": 6.138417778015136, "genuineness": 4.11766776561737, "identity": 0.5250219690799713, "wer": 0.007492941840767927, "valid_fraction": 1, "identity_delta": -0.02961778312921524, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.016640634613466584, "ci95_z": [ -0.33966795072896655, 0.2641015536117598 ], "language_deltas": { "en": 0.004003902919018132, "de": 0.1722656467567928, "fr": 0.27490240543641065, "nl": -0.6671874372594812, "es": 0.2992186552145925 }, "languages_improved": 4, "clear_gain": false, "delta_ce": 0.012708253860473633, "delta_genuineness": 0.05227941513061524, "delta_wer": -0.0010351966873706003, "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": 0.016640634613466584, "ci95_z": [ -0.33966795072896655, 0.2641015536117598 ], "language_deltas": { "en": 0.004003902919018132, "de": 0.1722656467567928, "fr": 0.27490240543641065, "nl": -0.6671874372594812, "es": 0.2992186552145925 }, "languages_improved": 4, "clear_gain": false, "delta_ce": 0.012708253860473633, "delta_genuineness": 0.05227941513061524, "delta_wer": -0.0010351966873706003, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 2.5622460409518295, "ci95_z": [ 2.0308007800441006, 3.0591600790471167 ], "language_deltas": { "en": 1.7017578328232057, "de": 3.0111327909961934, "fr": 2.847949127126917, "nl": 3.212792843058141, "es": 2.037597610754691 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.11866351127624512, "delta_genuineness": -0.19637734413146973, "delta_wer": -0.0009648033126293998, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 3.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793023986.4656286, "example": { "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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.", "language": "nl", "seed": 1702, "scale": 0.0, "cfg": 3.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "01072e12d07edf8336a7c1f88b586d695596ab7e49a4003121a553be4283c284", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41c48004432511d2a72cb18ef11a1d2f10c8cd5905a6798e9339f5451b26a25d", "generation_seconds_batch": 21.134620998986065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 5.824047088623047, "genuineness": 3.9676074981689453, "identity": 0.5107465386390686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/01072e12d07edf8336a7c1f88b586d695596ab7e49a4003121a553be4283c284.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "0116701e4086830b3028aad6dbd04be79ce2b88365a561030bffe285e2819b54", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0026334c704793e9a27e021657bb4bb9905bc3ac94a59a8bebe9e9fd4fb4c9c7", "generation_seconds_batch": 22.909438604023308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19309978187084198, "target_z": -0.15332031460821635, "ce": 6.38003396987915, "genuineness": 4.093128204345703, "identity": 0.1974245309829712, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0116701e4086830b3028aad6dbd04be79ce2b88365a561030bffe285e2819b54.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": "0138956ca786d185a82d2e45b254556c64083797f25ab0d4344641f55dcd5a8c", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5437ca71146f23f61a07c9035af997bb9c5b497c2a6491dbaaea3890a0587cc", "generation_seconds_batch": 15.51466859295033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.332108974456787, "target_z": 5.531249743640891, "ce": 6.213237762451172, "genuineness": 4.061748504638672, "identity": 0.40314391255378723, "hypothesis": "I 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_Astonishment_Surprise/0138956ca786d185a82d2e45b254556c64083797f25ab0d4344641f55dcd5a8c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "01bd5de176d8d4217a755160e0564f00736a0848d61d1844a6a312c99f2f10eb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "658638c76099adb7d426b943186e1214553a2569632000ca9acf123aafd42d0c", "generation_seconds_batch": 23.43496055295691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4166717529296875, "target_z": 2.062500080955508, "ce": 6.395919322967529, "genuineness": 4.519899368286133, "identity": 0.30360522866249084, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/01bd5de176d8d4217a755160e0564f00736a0848d61d1844a6a312c99f2f10eb.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "122fa3c31e4c1f5e366619029fe2dab3e25fa2909b3f0593e884114c652fc12c", "generation_seconds_batch": 17.09862250299193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04480437934398651, "target_z": -0.42187499325370764, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.6700679063796997, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-les bien, et vérifie 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_Astonishment_Surprise/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "024f1ab7c709497e505532e161425ae945350f4c1ce84901add209c893526a45", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bf9b19c2f5bde7e953535781151684dad6c86859b4f374387c0114494bae60bb", "generation_seconds_batch": 19.48433412902523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5547212362289429, "target_z": 2.312499973014831, "ce": 6.109982967376709, "genuineness": 4.030367851257324, "identity": 0.6318942904472351, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/024f1ab7c709497e505532e161425ae945350f4c1ce84901add209c893526a45.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "0278365b4663d733aa645b4c7b6b05e40df93ff621e1b1610fb8d3697eedad99", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "46fe38384b9f76e3bec1c2943b709553964daefb5ccc1f4e538e47a1439e9dda", "generation_seconds_batch": 18.67473128705751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9352166652679443, "target_z": 4.81249997301483, "ce": 6.205295085906982, "genuineness": 4.017816066741943, "identity": 0.5669562816619873, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast 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_Astonishment_Surprise/0278365b4663d733aa645b4c7b6b05e40df93ff621e1b1610fb8d3697eedad99.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": "028d71bd3d8dcb4d6c35355b58b0aaf1a3cde79e3a87935e07bb26df89736b1b", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4dab559bb73a4458bb0e78670146f44737c3bfa8209bb56b6f339cd69a71823", "generation_seconds_batch": 17.34405041008722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6401430368423462, "target_z": 0.6562500134925847, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.44533106684684753, "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_Astonishment_Surprise/028d71bd3d8dcb4d6c35355b58b0aaf1a3cde79e3a87935e07bb26df89736b1b.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": "039a1b0b5cc874bbe6e66a3d950ba815db7d3a516a36f9fdb30b92d1ffcbe43a", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05b9b67a00ca9cb3e3026096fd64b540d54998a150ed4263a24a22ab242b44c9", "generation_seconds_batch": 23.39177747699432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4109592139720917, "target_z": 0.2412109303320644, "ce": 6.268836498260498, "genuineness": 3.9927117824554443, "identity": 0.47213202714920044, "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_Astonishment_Surprise/039a1b0b5cc874bbe6e66a3d950ba815db7d3a516a36f9fdb30b92d1ffcbe43a.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "04a9629f4cb34345dda75a77c939fea8b56eabdca0a1fd2a8cd12538ba9ea8e2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "70e9c2070a95591c9b661b996e9c41900817f9fde33686058c648fb8351e9f8b", "generation_seconds_batch": 20.989322626963258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2685956358909607, "target_z": -0.01660154605591241, "ce": 6.197352409362793, "genuineness": 4.068024158477783, "identity": 0.25341108441352844, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/04a9629f4cb34345dda75a77c939fea8b56eabdca0a1fd2a8cd12538ba9ea8e2.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "04ed959b97c12291c4412d4db04640889594c7fa316aec6c67d2ec6067e0ebb7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f635434b5abe50b9ec088043506765d97d8f694137c9da400e4c4a4af183ae08", "generation_seconds_batch": 22.86378760403022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.088804006576538, "target_z": 1.4687499325370765, "ce": 6.173524379730225, "genuineness": 3.973883628845215, "identity": 0.3921721279621124, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/04ed959b97c12291c4412d4db04640889594c7fa316aec6c67d2ec6067e0ebb7.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "0576935d650ab71989d26e8274e7013afaec449e1fb0e653b7ca278320427567", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2b573a02280fe2d168d5b20933cd96e37b42ba040c3637ae7809634c36d4d94a", "generation_seconds_batch": 16.659024941036478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0974321365356445, "target_z": 1.4843749932537076, "ce": 6.109982967376709, "genuineness": 3.986435890197754, "identity": 0.4931161403656006, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0576935d650ab71989d26e8274e7013afaec449e1fb0e653b7ca278320427567.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "8035764d481d8c34d1e25350020ca968d264491df8e07038b8111ab86379bf76", "generation_seconds_batch": 16.798953515011817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2397956848144531, "target_z": 1.7421874156713457, "ce": 6.427689552307129, "genuineness": 4.3881025314331055, "identity": 0.43678757548332214, "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_Astonishment_Surprise/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "05a4dc3182c18e05292ee678547dd58139bfd1adec5544b5dd804806c9719c2a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acdd7ac4ed8d92f4b092d31ada206b9eb20c9bfd06395e89b0085ddb3380ad16", "generation_seconds_batch": 15.894112932030112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.48569655418396, "target_z": 2.187500134925847, "ce": 6.1020402908325195, "genuineness": 4.093128204345703, "identity": 0.6881468892097473, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/05a4dc3182c18e05292ee678547dd58139bfd1adec5544b5dd804806c9719c2a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "05d6887e9a34a874ca91e58f824421d2fd697def2da14f91f16a14f6e81fe0cd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3db42e4ed85126cdfca34ef16ea0c679e5e4c178f5d01cffe2beb8f440d8295f", "generation_seconds_batch": 23.305688870023005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05666801333427429, "target_z": -0.40039061572384804, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6526644229888916, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/05d6887e9a34a874ca91e58f824421d2fd697def2da14f91f16a14f6e81fe0cd.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "0617ed26f46c8c8ad9812f43e26caf2069a81816cb6c7408dc21c62c60c5e3fd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0c0f7275c7fb5fa4eb4fdaf94751bb2d6075e9381e16221e97be64a2ea7ed05c", "generation_seconds_batch": 21.720235493034124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5978617668151855, "target_z": 2.3906250607166313, "ce": 5.982900142669678, "genuineness": 4.231201171875, "identity": 0.5360193848609924, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0617ed26f46c8c8ad9812f43e26caf2069a81816cb6c7408dc21c62c60c5e3fd.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "061cd6bc4d83fb3650bd0df905f825c84e3c74506b99b9f594a59fbb09104e19", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c3cd43ad97dd076481286ea9bcd65843f24aa2fa4a69dbfc5e270edd742e4c13", "generation_seconds_batch": 22.406603661947884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4779274463653564, "target_z": 3.9843747773723526, "ce": 6.086154937744141, "genuineness": 3.998987913131714, "identity": 0.2551460266113281, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/061cd6bc4d83fb3650bd0df905f825c84e3c74506b99b9f594a59fbb09104e19.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "06729ac1aeb6a64f587a0fd947932eba883da506eaa3d7f5cb510b3d1443e40f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "81361b7706ef3019b3c49e4454b0f22adf451eae932da43b33494ac928c5e132", "generation_seconds_batch": 17.218848469899967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18555019795894623, "target_z": -0.16699218876492983, "ce": 6.181467056274414, "genuineness": 4.344170093536377, "identity": 0.583794116973877, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/06729ac1aeb6a64f587a0fd947932eba883da506eaa3d7f5cb510b3d1443e40f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "06aecfc8ad1eba677eb4c60689bdac290e22909dd8a2d8db0fccb1ffddcf5d4c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cdc3826f41188ddfd8623fa036b0261b210f00d97d48600bb0a289d642769fbc", "generation_seconds_batch": 19.932472829008475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.211315631866455, "target_z": 5.312499757133476, "ce": 5.903473377227783, "genuineness": 3.848362922668457, "identity": 0.32765763998031616, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! ¡Podemos mirar juntos lo que hay dentro!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/06aecfc8ad1eba677eb4c60689bdac290e22909dd8a2d8db0fccb1ffddcf5d4c.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "06d7819407f9321d5595a878fd5a9007fe9241cbe107b1393e19fcee25fee783", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5efbfa9fa74fb2c8887e32d04750c5f380b5b071e65e4643cba8f96035a657fd", "generation_seconds_batch": 22.979478438035585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.028407335281372, "target_z": 1.359374939283369, "ce": 5.7247633934021, "genuineness": 3.898571252822876, "identity": 0.42846906185150146, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/06d7819407f9321d5595a878fd5a9007fe9241cbe107b1393e19fcee25fee783.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "0711dcfce54d6bec0e6e4c8f6aba9e7cf354c741b5b432a2455a0826cd9b4b81", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2792de77ae995c9f9da2937a033488a83dcaef946459b4cfa4833eff807cb264", "generation_seconds_batch": 22.220952814095654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.211315631866455, "target_z": 5.312499757133476, "ce": 6.062326908111572, "genuineness": 3.9048471450805664, "identity": 0.5884724855422974, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0711dcfce54d6bec0e6e4c8f6aba9e7cf354c741b5b432a2455a0826cd9b4b81.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "072bc07fffb61ffe88bf583b31516f5a41db8e131711e7e4bf3b8a0b1f824df3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2fecaecf9a70a6808de8309845a3c8a4ee447b8e8f7c7bd6e8df2ea3787c6847", "generation_seconds_batch": 21.167305591981858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.848076581954956, "target_z": 2.843750094448093, "ce": 6.125868320465088, "genuineness": 4.406930446624756, "identity": 0.4804232120513916, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/072bc07fffb61ffe88bf583b31516f5a41db8e131711e7e4bf3b8a0b1f824df3.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": "07e6744b62f8510a124e17ad9e3cca49fa36c51ed0913b3539e0d1245925046e", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43128d9ac82f3eebd3f991e1e2a7b56600ad8244f2d91677432e5e816d6ba4de", "generation_seconds_batch": 17.169835173990577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847217321395874, "target_z": 1.031249959522246, "ce": 6.316492557525635, "genuineness": 4.250029563903809, "identity": 0.47422733902931213, "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_Astonishment_Surprise/07e6744b62f8510a124e17ad9e3cca49fa36c51ed0913b3539e0d1245925046e.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "08474cdca0da0123501eea807d6e88dcc0c3eb9800f416e65c6562af26665678", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "be6b253f6c0e8e6369e842a9b58733ffbc21921498e2c5560466b7520c0118b6", "generation_seconds_batch": 16.307427919004112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02539116144180298, "target_z": -0.45703124494028075, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.711479902267456, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/08474cdca0da0123501eea807d6e88dcc0c3eb9800f416e65c6562af26665678.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "089928a042b73821eb8fe164868db1db6be070392599176d7a3386bc66eff878", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e645688b98fc64ea45c90d55561f4e4a147450c182895c3b3902ad63316ac841", "generation_seconds_batch": 21.63060807203874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907874822616577, "target_z": 2.0156251146869697, "ce": 6.157639026641846, "genuineness": 4.042920112609863, "identity": 0.39278000593185425, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/089928a042b73821eb8fe164868db1db6be070392599176d7a3386bc66eff878.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "08e7f76eb939f5417b8a14865669322c68f52f142e8e4b94f5ae539daecff311", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f601a2f59ebfdc0c6327ed8a1b0139be0895840adeb61080b7f9f1407b652d11", "generation_seconds_batch": 21.429450061987154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7100269794464111, "target_z": 2.593749986507415, "ce": 6.332377910614014, "genuineness": 4.143336772918701, "identity": 0.5102306604385376, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/08e7f76eb939f5417b8a14865669322c68f52f142e8e4b94f5ae539daecff311.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "09110aaf5f8245ff065489198bb955c4ef196558d55e6df7b72137aa71cee9db", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "35018cec4e05baaacf82a337541d8f571e1cbdd28ce38ca1f33e9cd05e76b82a", "generation_seconds_batch": 24.184381363913417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7790517807006836, "target_z": 2.718750040477754, "ce": 6.086154937744141, "genuineness": 4.20609712600708, "identity": 0.5606645345687866, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/09110aaf5f8245ff065489198bb955c4ef196558d55e6df7b72137aa71cee9db.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "0915f2cfc8ca502463e2cbebb55a2f6b53a89125ec9dbf757c36651ff1ded191", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "56619aefbd5f041e09f5193e1a4b61f81fc648b25063b221081c14430b806b14", "generation_seconds_batch": 21.555222240043804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15858739614486694, "target_z": -0.21582031460821635, "ce": 6.054384231567383, "genuineness": 4.011539936065674, "identity": 0.5207648277282715, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0915f2cfc8ca502463e2cbebb55a2f6b53a89125ec9dbf757c36651ff1ded191.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "09782b103611b90331569625f6c2e9fae0f2587667b381c8775dc60395467b82", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f6631704cdd2699906f10ac2a894162b44e15e9d801da055ede1fdc8e639f54a", "generation_seconds_batch": 19.40746266208589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1586880683898926, "target_z": 3.406250121433262, "ce": 5.593709468841553, "genuineness": 3.848362922668457, "identity": 0.3356667160987854, "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_Astonishment_Surprise/09782b103611b90331569625f6c2e9fae0f2587667b381c8775dc60395467b82.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "0ab0641a3b23334a288791cb8558f88624faf7b0688d9a633422deb07f4f0fd6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5b0e9b69883bbb52f93bf7d27475dbd9e74acd6d3d2053739529ca7a0e298010", "generation_seconds_batch": 19.518389450968243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.211315631866455, "target_z": 5.312499757133476, "ce": 5.744620323181152, "genuineness": 3.9173994064331055, "identity": 0.6923540830612183, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0ab0641a3b23334a288791cb8558f88624faf7b0688d9a633422deb07f4f0fd6.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "0b0bb7348a434b1ecf59facdf85ab24e199c8d26453b8fcabb41c6ad8a44297c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a476e38f7fdc6ea2b137448b9973b97e0369834c304e9c562c4cf34496541d4a", "generation_seconds_batch": 23.04213024605997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5225852131843567, "target_z": 0.4433593707835673, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.6495711803436279, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0b0bb7348a434b1ecf59facdf85ab24e199c8d26453b8fcabb41c6ad8a44297c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "0b5c04917e1aa134b5a9b21449711608a12b83f8df6750382011c6a968fbdb02", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68a33fc53c3a416e67eb26f743b6f38e9fc94b75d709241b2e815face9dd5d10", "generation_seconds_batch": 23.05354540294502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3838775157928467, "target_z": 5.624999676177968, "ce": 5.967014789581299, "genuineness": 3.9927117824554443, "identity": 0.7777881622314453, "hypothesis": "J'ai trouvé la petite boîte ! Elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0b5c04917e1aa134b5a9b21449711608a12b83f8df6750382011c6a968fbdb02.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "0b93c457f7d1a3a7a61e18bb07bfa0e79b2515e460c98284ed4b2f0b8f5d2e9f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6e5145c8c05f56f67e577e578a5fd0dd0c074db5d72a434349067214042b21d7", "generation_seconds_batch": 21.720235493034124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.179399013519287, "target_z": 1.6328124224176381, "ce": 6.006728172302246, "genuineness": 4.2374773025512695, "identity": 0.45647358894348145, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0b93c457f7d1a3a7a61e18bb07bfa0e79b2515e460c98284ed4b2f0b8f5d2e9f.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "4f1b1f70b81cfa4d2df9764cda3db7c827f36edcecad9b13187fa20d77e289bf", "generation_seconds_batch": 15.710826231050305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059903547167778015, "target_z": -0.39453124494028075, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.48818230628967285, "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_Astonishment_Surprise/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.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": "0ce24f72681a92c514465fab753c168cd1dd0389893c21e37f84b8c221821dfe", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Your message arrived after I had left.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54140e803f2231203888a52dc69026e6fbbbe97bcfe0babb6a1f8409abe4b4cb", "generation_seconds_batch": 23.14467929804232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8731015920639038, "target_z": 1.0781249257907841, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.3609302341938019, "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_Astonishment_Surprise/0ce24f72681a92c514465fab753c168cd1dd0389893c21e37f84b8c221821dfe.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "0d10578c920d6dc2315bac9c9d9c16de6ff1b8d2eda3738682c2c322ae43435c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "54cc28824c3246942322d62e710cf47fc56bcfc3778cce4f0f69647741a01cf9", "generation_seconds_batch": 22.256812235922553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5547212362289429, "target_z": 2.312499973014831, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.6037163734436035, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0d10578c920d6dc2315bac9c9d9c16de6ff1b8d2eda3738682c2c322ae43435c.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "0d1561149d8aa52bc32fc1a1446ca6b8d0be72e54d6f44835c1be67b88417745", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2f19a678e7a7eb4cf57808a428630415c291884f1d68572618ecf862c6f9b84d", "generation_seconds_batch": 16.482200869941153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7100269794464111, "target_z": 2.593749986507415, "ce": 6.133810997009277, "genuineness": 4.011539936065674, "identity": 0.6854537725448608, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0d1561149d8aa52bc32fc1a1446ca6b8d0be72e54d6f44835c1be67b88417745.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "0d27306af85eacca3b7f9a54dd989726d8c5c01184f514505b1fe909511c3baf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "220404a8a571ac7cd59d3d713f74bc33e4be7a5cfc56d7b1c3acd07f74b41aa9", "generation_seconds_batch": 16.1252463349374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8912169933319092, "target_z": 2.9218749662685384, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.6121639013290405, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0d27306af85eacca3b7f9a54dd989726d8c5c01184f514505b1fe909511c3baf.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "0db72a7b2ea1bb8f844d55f0afe37450d8f45d75a8f264190534f19ab0241486", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e3923d5c7c64dbdf42d350c80b13f6ba8af0b9c274bf91a8cc404be8cd30992d", "generation_seconds_batch": 22.18526918592397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07608123123645782, "target_z": -0.36523436403727494, "ce": 6.149696350097656, "genuineness": 4.425758361816406, "identity": 0.7783324122428894, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0db72a7b2ea1bb8f844d55f0afe37450d8f45d75a8f264190534f19ab0241486.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": "0de7767bb4a26619526ee48093b4a98e7143c0e9ccd2ebd965cde19c17a6dee9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4946ba3c899ccabe711f93d398bd965126b4680942d6d0e27a2cc529f05be542", "generation_seconds_batch": 16.716558458982036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7790517807006836, "target_z": 2.718750040477754, "ce": 6.157639026641846, "genuineness": 4.444586753845215, "identity": 0.597658634185791, "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_Astonishment_Surprise/0de7767bb4a26619526ee48093b4a98e7143c0e9ccd2ebd965cde19c17a6dee9.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "0e3761131cdbb89644c72541f8ff6e20220526bf36efc7f074503a82ef766530", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fa117bae2fb4dcd93c8660290939ddd29a09678191e6da12ab2c908a9c7b4bee", "generation_seconds_batch": 15.928920018021017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9550685882568359, "target_z": 1.2265625708360697, "ce": 6.117925643920898, "genuineness": 4.356721878051758, "identity": 0.5995221138000488, "hypothesis": "Encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0e3761131cdbb89644c72541f8ff6e20220526bf36efc7f074503a82ef766530.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "0e447542fe1d56f4c6c37453bbd71a593f8334dceb08eb5fed7023654d0708a0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ad73b8e0077c1a8fee7f8d226a4106a640eaff2790c6e409cbc77d197864bfb9", "generation_seconds_batch": 20.51120628893841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005977928638458252, "target_z": -0.4921875236120232, "ce": 6.403861999511719, "genuineness": 4.18099308013916, "identity": 0.4626051187515259, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0e447542fe1d56f4c6c37453bbd71a593f8334dceb08eb5fed7023654d0708a0.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "0e61a968e5bd96e2b7af068b867d17630a9b1c87c2294c78f85d77337d010928", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "21eb2f9c6f70be89ebdb8845f5fa2cc7ed72204f46d4b7eb3915891e1027f6a8", "generation_seconds_batch": 17.134250031085685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.150059938430786, "target_z": 3.3906250607166313, "ce": 6.213237762451172, "genuineness": 4.105680465698242, "identity": 0.532477855682373, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0e61a968e5bd96e2b7af068b867d17630a9b1c87c2294c78f85d77337d010928.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "0ed9d25e02537a0be72e29bbecedcd785e0fda71f03e3d602b10d2405e558181", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dc6b6a586446103e07a0c844b6bc5950a79bd1649727cf4932528a56a7a27e14", "generation_seconds_batch": 21.19205417507328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036176279187202454, "target_z": -0.4375, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.6841426491737366, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0ed9d25e02537a0be72e29bbecedcd785e0fda71f03e3d602b10d2405e558181.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "0f6e08a17fb5d0fb233ca739c18d4c5b598eaf5f13361e3d4d090277a322bdc8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0bae8f60e3fb0e7911c8ff32173d4505f2b484283ec756d06e10100001ac9435", "generation_seconds_batch": 23.145758813945577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0370354652404785, "target_z": 1.375, "ce": 6.316492557525635, "genuineness": 4.381826400756836, "identity": 0.3773382306098938, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/0f6e08a17fb5d0fb233ca739c18d4c5b598eaf5f13361e3d4d090277a322bdc8.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": "0fa6bd8e83047bc28d3070934c318e47a3aa7fee7152f6f7b0e42b6233ac5cc4", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7dbbef785bcdcbe7fc16825c18e82e0e5f39df398f9aec0c62a1e23824db9b2", "generation_seconds_batch": 21.005876864073798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6237460374832153, "target_z": 2.437500026985169, "ce": 6.24500846862793, "genuineness": 4.024092197418213, "identity": 0.4103637933731079, "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_Astonishment_Surprise/0fa6bd8e83047bc28d3070934c318e47a3aa7fee7152f6f7b0e42b6233ac5cc4.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": "0fd3a6a72b9a87914723eafb9ca65ab1c87caeeb3aa88c83780c92d2c89acdba", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "243c112e92adf29a62a20a5fe779e2a6c9f35db14a8a298da317e9532d1fdcea", "generation_seconds_batch": 21.005876864073798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0370354652404785, "target_z": 1.375, "ce": 6.268836498260498, "genuineness": 4.080576419830322, "identity": 0.3191037178039551, "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_Astonishment_Surprise/0fd3a6a72b9a87914723eafb9ca65ab1c87caeeb3aa88c83780c92d2c89acdba.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "104cb4dbfd213fb97c9fc5845024997d43ee878a90894b5f97909c04980aef0a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aa0295f94953e2cceb98da1a7807544298a1a6929be6c82bad39f986457710d2", "generation_seconds_batch": 21.754361297003925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5495480298995972, "target_z": 0.4921875236120232, "ce": 6.0146708488464355, "genuineness": 4.143336772918701, "identity": 0.6719093322753906, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/104cb4dbfd213fb97c9fc5845024997d43ee878a90894b5f97909c04980aef0a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "10dd43e6d32c264ad6447cf665082411475ea0a53aba7cc1596f6583681aed95", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a053eff6b1086f5ad103c114036eaf252cdccb3404e7e5d54ae9faee09c684da", "generation_seconds_batch": 17.366010625031777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.968010663986206, "target_z": 1.2499999460296611, "ce": 5.77639102935791, "genuineness": 4.111956596374512, "identity": 0.4654936194419861, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/10dd43e6d32c264ad6447cf665082411475ea0a53aba7cc1596f6583681aed95.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": "10fd824ac661456297ad915c298973e3d37de8e4fa40d528ccb09285719b11d3", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6af6dd0f87f67f56517e22b3ec351c2e4fec162a17d2b32568a8118106b65489", "generation_seconds_batch": 22.768792065093294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7531675100326538, "target_z": 2.6718750742092157, "ce": 6.109982967376709, "genuineness": 4.18726921081543, "identity": 0.24964496493339539, "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_Astonishment_Surprise/10fd824ac661456297ad915c298973e3d37de8e4fa40d528ccb09285719b11d3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "11aaf024466871f612580c4dcea57a02a43e5b5024f3e1c59331e2670a8b6184", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "447caefa834e9486cb30f15eb1aef8227ab9a74343d7b61a8c9695b7969131cb", "generation_seconds_batch": 22.690680117928423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6487711668014526, "target_z": 0.6718750742092158, "ce": 6.086154937744141, "genuineness": 4.2751336097717285, "identity": 0.47657352685928345, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/11aaf024466871f612580c4dcea57a02a43e5b5024f3e1c59331e2670a8b6184.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "12198cd323412703793c44430e14317713eae54d3bbf9d25bccc7301366c8258", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ea7dbc2bd9a4e1df38df4f427742dfe1d60c6a9dd171d3c9bec88a78c38e4a6a", "generation_seconds_batch": 19.65854459500406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4011337757110596, "target_z": 5.656249797611229, "ce": 5.879645347595215, "genuineness": 3.8546390533447266, "identity": 0.5344501733779907, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/12198cd323412703793c44430e14317713eae54d3bbf9d25bccc7301366c8258.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "1233a8de5ed8966e7346ff3bb88daa65497deb374ce218c75052d6022c3613a8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f4ff7a887055ddcc497555754a727252731a645ba38da89ceb9e51e67485a81", "generation_seconds_batch": 23.456347284954973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5719774961471558, "target_z": 2.343750094448093, "ce": 5.919358730316162, "genuineness": 4.042920112609863, "identity": 0.6234375238418579, "hypothesis": "J'ai trouvé la petite poêle. 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_Astonishment_Surprise/1233a8de5ed8966e7346ff3bb88daa65497deb374ce218c75052d6022c3613a8.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "12a60cf60a67262390ffab9450e89bf62aa2c2530dfb81edbb841508339323ff", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "82bd752ebd102137ab58cfbe38b03d3e83043116d5c1f6954ec5f3bce54b8f47", "generation_seconds_batch": 14.086939547909424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7617956399917603, "target_z": 2.687500134925847, "ce": 6.213237762451172, "genuineness": 3.8295347690582275, "identity": 0.3901425004005432, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/12a60cf60a67262390ffab9450e89bf62aa2c2530dfb81edbb841508339323ff.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85990f8119be05d3a711277c74afdb4db17c38d140253960033e8704eb00464e", "generation_seconds_batch": 16.0340065889759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2397956848144531, "target_z": 1.7421874156713457, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.6221774816513062, "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_Astonishment_Surprise/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "13bea4c9129a2005345dbb2866347a571431eefde827cef57e767366a6450350", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4a3ac5a267407e4d29882d4945410e6937e53f5f1b0b6956964654a4c678742f", "generation_seconds_batch": 23.12088602001313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9334982633590698, "target_z": 1.187499919044492, "ce": 5.808161735534668, "genuineness": 4.268857479095459, "identity": 0.5805078744888306, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/13bea4c9129a2005345dbb2866347a571431eefde827cef57e767366a6450350.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "144443b874fdb0177be9249ce340fffc2620439ab4a9aaa4a0fffe14280ac335", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "59c2645f148ee0f8e5826a652123bd9f1da70e2c0576d370e6dc359d936972e0", "generation_seconds_batch": 16.45473897503689, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.339777410030365, "target_z": 0.1123046651529066, "ce": 5.990842819213867, "genuineness": 4.18099308013916, "identity": 0.7334256768226624, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/144443b874fdb0177be9249ce340fffc2620439ab4a9aaa4a0fffe14280ac335.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "14aff03cc2c057331dd465137e23822310158293428b3bf1026d031437020fb6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "76bad8f6d60a97254eaee1cf3d7112a3e9b2d454eae4deea4942e1de29e4b4d8", "generation_seconds_batch": 22.249897071975283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17746135592460632, "target_z": -0.1816406292164327, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.5782452821731567, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/14aff03cc2c057331dd465137e23822310158293428b3bf1026d031437020fb6.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "902a49593f9c8c1c7677b433f9b9f293a3d3d4c7954e0c1384d4e0d14fdbba35", "generation_seconds_batch": 15.851573260035366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024312645196914673, "target_z": -0.45898437752985966, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.32384103536605835, "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_Astonishment_Surprise/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "1584f970ccdc9182bcc9c4d51863c4398845c4f461cc3b1959d1913319afa2d4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2dcf5d9e0f6e95458e1e84a265070a66550efda42482c08329bc017d5f844443", "generation_seconds_batch": 22.14725066605024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35757285356521606, "target_z": 0.14453121795511137, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.7660643458366394, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1584f970ccdc9182bcc9c4d51863c4398845c4f461cc3b1959d1913319afa2d4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "15b1c98be1ab9c31967ffeaff188f924219fa0708800c781e235106cda2c8d0d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0dd8806e08b535feb60b8626c4c4bc120940eaba55605e3eb1fb02f264a8e39f", "generation_seconds_batch": 23.121724072028883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3838775157928467, "target_z": 5.624999676177968, "ce": 6.157639026641846, "genuineness": 3.9801597595214844, "identity": 0.5378838181495667, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/15b1c98be1ab9c31967ffeaff188f924219fa0708800c781e235106cda2c8d0d.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "15df11fa4d6fc5f1187ccf03ca893ed49dc5ded87b178bba756ba604c588d52a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa16c7b5f9a429cdb0592640f0568d6776b80a5c6eb2eb25a5ee86712f05d9a8", "generation_seconds_batch": 21.680496993940324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8687875270843506, "target_z": 1.0703123954324687, "ce": 6.252951145172119, "genuineness": 4.293961524963379, "identity": 0.3831508755683899, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/15df11fa4d6fc5f1187ccf03ca893ed49dc5ded87b178bba756ba604c588d52a.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "16795679e8f2036d905e8f741c286f4cad205f7d0c6b11017a859b4f070e7093", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1d2ba503efd019b29f3b11fa1ba22dd1d2332db66617b0867c1e6e44208ee156", "generation_seconds_batch": 21.00783088908065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.831679344177246, "target_z": 4.624999676177968, "ce": 5.974957466125488, "genuineness": 4.13078498840332, "identity": 0.09978953003883362, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/16795679e8f2036d905e8f741c286f4cad205f7d0c6b11017a859b4f070e7093.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "1683ec75c0f16345fac0cd30745e21530d17120fad6b2bc93c60cd8b9ba871b0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "646aaf73bbdc66f02e883ef2797bce26ccfd44bf4796b07026c5efc76fa3828a", "generation_seconds_batch": 21.548883691080846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348505973815918, "target_z": 3.749999730148306, "ce": 5.871703147888184, "genuineness": 3.9299514293670654, "identity": 0.023057762533426285, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1683ec75c0f16345fac0cd30745e21530d17120fad6b2bc93c60cd8b9ba871b0.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "16dc21073644be931482e369d13bb76fb1bad8293bfb9391b34394f75779e630", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "21033e8609710167a1f79d4375155e8432ad6b73c68a8871ac5db8387212ec82", "generation_seconds_batch": 21.14287537103519, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.07326602935791, "target_z": 5.062499649192798, "ce": 5.534139156341553, "genuineness": 4.017816066741943, "identity": 0.47336632013320923, "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_Astonishment_Surprise/16dc21073644be931482e369d13bb76fb1bad8293bfb9391b34394f75779e630.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "16e1ca451dd22396e9384ab744d5ce45dd05c25bffd7afc483fbf2fbcee9d1ba", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "49f0b0a7aec8fb6fb0db694f12e3f1fd147bfaf0aec849f7900cbc144569ecbe", "generation_seconds_batch": 23.34059741697274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.022356986999512, "target_z": 6.781250283344279, "ce": 5.550024509429932, "genuineness": 3.7040140628814697, "identity": 0.3019341826438904, "hypothesis": "¿La puerta sigue abierta? ¡He dejado tu abrigo! ¡Sobre la silla! ¡Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/16e1ca451dd22396e9384ab744d5ce45dd05c25bffd7afc483fbf2fbcee9d1ba.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "179e96f68ac136022fc5bd9baec9d35835caef7e5f8b70f2b942fbefe891d2c0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f1b4b3c536b46b8d0987340d24f2812e5542373baae74c2ae28e423ee5211943", "generation_seconds_batch": 21.468072083080187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7790517807006836, "target_z": 2.718750040477754, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.40972277522087097, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/179e96f68ac136022fc5bd9baec9d35835caef7e5f8b70f2b942fbefe891d2c0.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": "17d8e4f50cfc6b0dd435cf8c8a1088034dee837dc85b50495dc234c8dca38517", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7a54acf585b4d727f3166856fb92309b1f1a4d5a748399cc7c8025429cbff657", "generation_seconds_batch": 14.086121891974472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9429856538772583, "target_z": 3.0156251146869697, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.5705686807632446, "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_Astonishment_Surprise/17d8e4f50cfc6b0dd435cf8c8a1088034dee837dc85b50495dc234c8dca38517.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "1814cc96e8a7c083fd711bb1ba423a7396f12f5e69eea7ea6c3517f1814da785", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a14732a63eb8fa19ba3805829fc7205b0e466a78b562bfac7f1c68e87a7fece6", "generation_seconds_batch": 20.920698574976996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06637461483478546, "target_z": -0.38281250337314615, "ce": 6.038498878479004, "genuineness": 4.482243061065674, "identity": 0.6384692192077637, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1814cc96e8a7c083fd711bb1ba423a7396f12f5e69eea7ea6c3517f1814da785.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "18809adce72f713f658713c603e313a5ac710127bc4bc305c232a5fc73f79d4d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0b4329be2bf1ec4d89e9c924e12760348a00a51bd51dbb0ee60fa6243618f060", "generation_seconds_batch": 23.12088602001313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5430769324302673, "target_z": 0.4804687280745499, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.6312851905822754, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/18809adce72f713f658713c603e313a5ac710127bc4bc305c232a5fc73f79d4d.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "189b86047fbc65749758098baddb8a4d8fcae7945d45a0342a59aac5975e6fa3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "26ec00d97f704cd1c1df90bb3fb31750e6baa925f973a94a4ae312173460dacf", "generation_seconds_batch": 17.316645040060394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7328950762748718, "target_z": 0.8242187685523039, "ce": 5.959072113037109, "genuineness": 4.13078498840332, "identity": 0.46279120445251465, "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_Astonishment_Surprise/189b86047fbc65749758098baddb8a4d8fcae7945d45a0342a59aac5975e6fa3.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "18d1d4ca033bebcc0f07cc3933a2ddc91836435927f032e9c1201b68fb2dac4c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e949531afee906f13b354e4d324f8026ebbb675283cdb8ed10c68961486504f3", "generation_seconds_batch": 21.012840693001635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4425560235977173, "target_z": 2.1093750472240465, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.41713225841522217, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/18d1d4ca033bebcc0f07cc3933a2ddc91836435927f032e9c1201b68fb2dac4c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "18dfd8954946819d2eb9dda6deff1737c06140cd0140fe1c2aa2c20f7cd94ec3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "94b1b1f8105dbc318d69512cd9380383551e8fabb485b325e97109eaf0a1bb02", "generation_seconds_batch": 19.835043646977283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7911347150802612, "target_z": 0.9296874966268538, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.6005592346191406, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/18dfd8954946819d2eb9dda6deff1737c06140cd0140fe1c2aa2c20f7cd94ec3.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "18e61f0ea3bf87494f2779618208219b8c003300036a2c5972c2febba6ffdd1a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 129, "seconds_generated": 10.32, "mp3_sha256": "747975047158aa5cea53b5c3fdd7205ad38ee0fb42fcae4501bc9f7b191a6422", "generation_seconds_batch": 23.337108843959868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348505973815918, "target_z": 3.749999730148306, "ce": 5.669164657592773, "genuineness": 3.8797430992126465, "identity": 0.5830727219581604, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la bite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle.", "wer": 0.42105263157894735, "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_Astonishment_Surprise/18e61f0ea3bf87494f2779618208219b8c003300036a2c5972c2febba6ffdd1a.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "191b008dfa694b999a66ee4f055b0aa8b0ff0b40d22bd6ea54d26f8d7739bb63", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a8c5477bedc4f32b5c925eff416269bb580a7fae93e3c9d47585ad07d512736", "generation_seconds_batch": 22.87103564699646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4082629382610321, "target_z": 0.23632812584328655, "ce": 5.863759994506836, "genuineness": 4.080576419830322, "identity": 0.5183145999908447, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/191b008dfa694b999a66ee4f055b0aa8b0ff0b40d22bd6ea54d26f8d7739bb63.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "192719556583e7a66a01b14042e0bd3345eb5b557a0d651027cd44bc8850bd85", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6dad2e65445a1f9a542db042d5ef2158114d392c4cf4f70747e6704473e2f607", "generation_seconds_batch": 20.38187185698189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3994154930114746, "target_z": 2.031249959522246, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.6912428140640259, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/192719556583e7a66a01b14042e0bd3345eb5b557a0d651027cd44bc8850bd85.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "192f7abf8e27efdcff6c4195972514c019f1f40be3e8fd390f625c07b6d413ff", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "344a05413e06dff60153e12aff267d40b6e2f33a4c527ad86c28ee1703dfe167", "generation_seconds_batch": 22.504650617018342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8825889825820923, "target_z": 2.906250121433262, "ce": 6.157639026641846, "genuineness": 4.444586753845215, "identity": 0.6626814007759094, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/192f7abf8e27efdcff6c4195972514c019f1f40be3e8fd390f625c07b6d413ff.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "195290fe5d9732caf077910755ea665474126eff39b20c25c754d0b256ff2168", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2212d30f07a79be4b28424b18206c279bd97dfe96d94f7e6bfe385f6c51a766c", "generation_seconds_batch": 21.55313129001297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 6.348263263702393, "genuineness": 4.344170093536377, "identity": 0.4363819658756256, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/195290fe5d9732caf077910755ea665474126eff39b20c25c754d0b256ff2168.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "197c7add962a095b8155ed721d7f2efe549ad6dfa7a21ddab5d02b88f47ff0b8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "462ee0192e72503ce45cd662831e2f41abecadcf8c35a823e13281c79598f0c4", "generation_seconds_batch": 24.801731627085246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9334982633590698, "target_z": 1.187499919044492, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.4641694724559784, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/197c7add962a095b8155ed721d7f2efe549ad6dfa7a21ddab5d02b88f47ff0b8.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "1994347baf6544c6064be95f248c65dbb1c9420e54f8cbdaf0c75c23ae8e99f5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "54c0fb966325d1102ba201a2d6872ed0a83bca3d1354aaa6a84830dfd843c46d", "generation_seconds_batch": 23.56130184594076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.425299882888794, "target_z": 2.0781251416721394, "ce": 6.157639026641846, "genuineness": 4.457139015197754, "identity": 0.7438387870788574, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1994347baf6544c6064be95f248c65dbb1c9420e54f8cbdaf0c75c23ae8e99f5.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "1a3d9059bb6704895984ccedf14203cde857fe8d31af4efd78c32b5a29b908c2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bbf9c98e72a996f19c1f06e64000d7677fbb123a350446e2b875ec57a64b6b08", "generation_seconds_batch": 20.51120628893841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15696963667869568, "target_z": -0.2187499865074153, "ce": 6.443574905395508, "genuineness": 4.400654315948486, "identity": 0.35316580533981323, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1a3d9059bb6704895984ccedf14203cde857fe8d31af4efd78c32b5a29b908c2.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "1a8397a66692ad4738dff60c49de69f0d08f7f1c85ef05d7c8a08b86be9e1e04", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c3f254fcc55fc42850d332e0c687d2fe3a0db79079f677d9cd8ecde334d9333b", "generation_seconds_batch": 20.128429287928157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0413495302200317, "target_z": 1.3828125303583156, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.48132550716400146, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1a8397a66692ad4738dff60c49de69f0d08f7f1c85ef05d7c8a08b86be9e1e04.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "1ad7465a5cc92c40a6587eeb17edd1c01fbecade0a269ff24da8e7b9394b8996", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "525a31f4519243387f9dee8c2e604b3642d7929ae4ff4745509167e1c38ad2bb", "generation_seconds_batch": 23.28264883707743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968869924545288, "target_z": 3.062500080955508, "ce": 5.967014789581299, "genuineness": 3.986435890197754, "identity": 0.63661128282547, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1ad7465a5cc92c40a6587eeb17edd1c01fbecade0a269ff24da8e7b9394b8996.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "1b1eefa0bbbbbbfa99dab7133c06b9d2c531d73d39bc311cadf68f24a7362fb4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6e8afe102462c1c4b3cbc6b661f82c644286f46f2264ae0ccca53602b99783ed", "generation_seconds_batch": 22.702861806959845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5495480298995972, "target_z": 0.4921875236120232, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.566500723361969, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1b1eefa0bbbbbbfa99dab7133c06b9d2c531d73d39bc311cadf68f24a7362fb4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "1c81c6229412723d501b598183ead686d36876ca3d78720563626c9769c82e0d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d42cdc460a2e8038c59d63a354e2c5cc56434a50309d6acc60bf2ab6cc4b8f38", "generation_seconds_batch": 15.894112932030112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 6.125868320465088, "genuineness": 3.9927117824554443, "identity": 0.5987931489944458, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1c81c6229412723d501b598183ead686d36876ca3d78720563626c9769c82e0d.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "1d1b49fc9440537fc9873295c29c08dcfd0214b4b42cf80df69b3e85eeec1bfa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b0879d02e265861283b154705b0e6c6a69e17720b4a5a79d8901bbf33b4069ab", "generation_seconds_batch": 22.736944678938016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1146882772445679, "target_z": 1.515624898805615, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.7531682252883911, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1d1b49fc9440537fc9873295c29c08dcfd0214b4b42cf80df69b3e85eeec1bfa.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "91490529d79359b9cc498ec5dde39f59a522d6ad175cd20f902cfacce16a9175", "generation_seconds_batch": 14.21704917808529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04480437934398651, "target_z": -0.42187499325370764, "ce": 6.133810997009277, "genuineness": 4.193545341491699, "identity": 0.5715569257736206, "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_Astonishment_Surprise/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.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": "1d7746a747d7ef2a06a10a77f099624ac18f37af2819614bc3d0d8d6af349b05", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "564713a16b020bfef9e2eb0fd0cd3cfb19a4cd9191817dfa7a277abba745e55a", "generation_seconds_batch": 22.662932388018817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.228571891784668, "target_z": 5.343749878566737, "ce": 6.181467056274414, "genuineness": 3.9048471450805664, "identity": 0.616416335105896, "hypothesis": "De sleutels liggen op de keukentafel. keek in de la en daarna naast het raam. Neem ze mee als je weggaat!", "wer": 0.045454545454545456, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1d7746a747d7ef2a06a10a77f099624ac18f37af2819614bc3d0d8d6af349b05.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "16cc88b94f8d8210b4e04211ab0cae4b1ccedebe487aecf7e231deeb89f6d3d2", "generation_seconds_batch": 16.508034121943638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16344070434570312, "target_z": -0.20703124494028075, "ce": 6.260893821716309, "genuineness": 4.15588903427124, "identity": 0.5060300827026367, "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_Astonishment_Surprise/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "1d9adee9f8e5f35e1f170f721dc9297595f9c22d808828edddf18bb3bd1dd3f0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "58ebdbfe32d7319a7ae41f936c75871bd0e365c85840f37a54af2007ce8367c3", "generation_seconds_batch": 23.197484750067815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5210678577423096, "target_z": 4.062499649192798, "ce": 5.974957466125488, "genuineness": 4.061748504638672, "identity": 0.2946479320526123, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1d9adee9f8e5f35e1f170f721dc9297595f9c22d808828edddf18bb3bd1dd3f0.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": "1dc52c2b5fede46f1c63def73f9cea8b2cc927d33796ff062711fe56a84e72b4", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8264e21e3c91579d144c80d8adf3ccf4e08953638982daab6029a6b8a9859305", "generation_seconds_batch": 23.09230534301605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.211315631866455, "target_z": 5.312499757133476, "ce": 6.252951145172119, "genuineness": 4.3881025314331055, "identity": 0.349189817905426, "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_Astonishment_Surprise/1dc52c2b5fede46f1c63def73f9cea8b2cc927d33796ff062711fe56a84e72b4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "1dc776483fdcbada9e9edad8fadbfaa06c1e7c721a0b71e46008be893ef1f502", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0678b34a512b0bca8d50dc52dbccfa0207972d0049c8bcd2f13d13a430fe44a2", "generation_seconds_batch": 24.184381363913417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8213330507278442, "target_z": 0.9843749932537077, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.5988927483558655, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1dc776483fdcbada9e9edad8fadbfaa06c1e7c721a0b71e46008be893ef1f502.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "1e45c142b50e6cce28467a35dc3ebd43a86ffdc52e7cc23d8a13c97debb046cc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "12b476b067342642458c2af811de0c8aad2087f68c7f6adfda7a165d495045ba", "generation_seconds_batch": 22.256812235922553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7100269794464111, "target_z": 2.593749986507415, "ce": 6.173524379730225, "genuineness": 4.300237655639648, "identity": 0.264739990234375, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1e45c142b50e6cce28467a35dc3ebd43a86ffdc52e7cc23d8a13c97debb046cc.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "2bb5e6b3b5f8b2bd6809c242f1b68c8a361e682f2bc89af407c5d525d4d970d8", "generation_seconds_batch": 14.21704917808529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13324236869812012, "target_z": -0.2617187415671346, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.5746746063232422, "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_Astonishment_Surprise/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "1ec9fa1f6de6dc42914e79c83d3b98cbe34378b70fded7bbbde9d03db70b6878", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8b19ddc6d8dd3beac9f6bde327f70c1f4c38d13ed833f50090b100fb60abce35", "generation_seconds_batch": 20.87781484099105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01460602879524231, "target_z": -0.47656251686573087, "ce": 6.467403411865234, "genuineness": 4.049196243286133, "identity": 0.5561357140541077, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1ec9fa1f6de6dc42914e79c83d3b98cbe34378b70fded7bbbde9d03db70b6878.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "1ed062a2be1b78732c90578afca7eaa47979c3f0554b7ab9bde448c0a5f65ba3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "529607663948d98c54af8e138a976130eee34cf50bbbdb1e690535fe350c0fe2", "generation_seconds_batch": 23.072132674977183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35541585087776184, "target_z": 0.14062500674629236, "ce": 6.046441555023193, "genuineness": 4.369274139404297, "identity": 0.5654360055923462, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1ed062a2be1b78732c90578afca7eaa47979c3f0554b7ab9bde448c0a5f65ba3.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "1ed2a6de51cce331275432812e1475e1ee62989f176876242a8f85e5039ce56e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4af10b43812d13fafd9d2f90b5235d341b1380918cb7c283cfe3d65a32eca4c5", "generation_seconds_batch": 24.801731627085246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18447169661521912, "target_z": -0.16894529436933933, "ce": 6.0305562019348145, "genuineness": 4.369274139404297, "identity": 0.7607235908508301, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1ed2a6de51cce331275432812e1475e1ee62989f176876242a8f85e5039ce56e.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "1ef0e9b37a7688f7d9d33773b126030c62f28af6ab1ea9dd7084a974960e832c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2da85ad4194dbe1d0c41e00c370ddbefc2f721a2b713c53689683fccf01a33ab", "generation_seconds_batch": 15.990324640995823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0378947257995605, "target_z": 3.187500134925847, "ce": 6.2767791748046875, "genuineness": 4.375550270080566, "identity": 0.5377343893051147, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1ef0e9b37a7688f7d9d33773b126030c62f28af6ab1ea9dd7084a974960e832c.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "1f558d196b7953832606f002869882a63d1a2fa932e0f487ab988d8273b6da88", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "135a0408b1de7d2ad27d528d1753fce0681b7c5c608472a4c2d7164504175e2b", "generation_seconds_batch": 22.225415159016848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07931676506996155, "target_z": -0.35937499325370764, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.5328254699707031, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1f558d196b7953832606f002869882a63d1a2fa932e0f487ab988d8273b6da88.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "1f7502c0135c2d33366be4a7331217fb99808cb3ba062d4bbdfac3982ae0c7ea", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "58e7ff2ba327e73d879ed12a410070617abaca96fd4931714f4b40a1b159943e", "generation_seconds_batch": 16.482200869941153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8739608526229858, "target_z": 2.8906250607166313, "ce": 5.990842819213867, "genuineness": 3.9550557136535645, "identity": 0.5958272218704224, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1f7502c0135c2d33366be4a7331217fb99808cb3ba062d4bbdfac3982ae0c7ea.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "1f76ae8eebe8adea263d01fc62a16f5b74586526d41e38e27b7234bb146fee9d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aa07370bb5adcb1ca7d84be5b72ebdf1952d7e0e8ddbc0020c3c8ac4ec8ed3af", "generation_seconds_batch": 21.318034525960684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.022356986999512, "target_z": 6.781250283344279, "ce": 5.8875885009765625, "genuineness": 3.6914620399475098, "identity": -0.016940049827098846, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1f76ae8eebe8adea263d01fc62a16f5b74586526d41e38e27b7234bb146fee9d.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "1f8c58600386d8acfce9afb06eb1e49459c10d0865421c40eb71eecd28de022b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0df32bb980b443255c64bbdadc02ed96277fd2417ed06e0383eeadb0af4fed68", "generation_seconds_batch": 22.225415159016848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22599440813064575, "target_z": -0.09374998650741531, "ce": 6.173524379730225, "genuineness": 4.375550270080566, "identity": 0.38311734795570374, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/1f8c58600386d8acfce9afb06eb1e49459c10d0865421c40eb71eecd28de022b.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "20033725071a2455b0d2534268dee7aeb4f56d11e1724b43d52412997e7b0cda", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "569b02c1920260b067bdfd5961107a3a3a5f353368929fd5bd4f890c8953cbf1", "generation_seconds_batch": 20.384269289905205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3830184936523438, "target_z": 3.812499973014831, "ce": 6.395919322967529, "genuineness": 4.381826400756836, "identity": 0.3892527222633362, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/20033725071a2455b0d2534268dee7aeb4f56d11e1724b43d52412997e7b0cda.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "2091098beb4136694c487328986079dba94406406830bd6a0e98aefbcefc5032", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f903ffe2ddc179ebd663cbcffc64f53437982139615e1ae8c1037db1431c8179", "generation_seconds_batch": 15.7211341150105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2626638114452362, "target_z": -0.027343748313426914, "ce": 6.133810997009277, "genuineness": 4.281409740447998, "identity": 0.3654692769050598, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2091098beb4136694c487328986079dba94406406830bd6a0e98aefbcefc5032.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "211f68822084ef57155ff30126312b88b894a36710b3e7b80c67a3c776bee53b", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ff13f3d7fdb7acc751601407fcc4d426ac18e9f52b3466a51be771717da12187", "generation_seconds_batch": 13.970532239996828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3640439510345459, "target_z": 0.1562500134925847, "ce": 6.078212261199951, "genuineness": 3.8922953605651855, "identity": 0.4057132601737976, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/211f68822084ef57155ff30126312b88b894a36710b3e7b80c67a3c776bee53b.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "215a096c6e828fc0d4ab9c45e3461fbca7a4aaaeb3a914ec13d19a31513c2cc3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e10a6fa505a70a1caf66e62743a55013682879e4a12416ab52d4f2c13fab93ef", "generation_seconds_batch": 21.61612341296859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3994154930114746, "target_z": 2.031249959522246, "ce": 6.3641486167907715, "genuineness": 4.243753433227539, "identity": 0.3215303421020508, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/215a096c6e828fc0d4ab9c45e3461fbca7a4aaaeb3a914ec13d19a31513c2cc3.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": "21aa3ea37eb3a1d54b5164486a325f796289e76bb6429e8a22686c492e548f12", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e80af0dab53f41acac67338353b9939764374d3f926a5fbac5cfe9dfb32879e", "generation_seconds_batch": 17.827229888993315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227712631225586, "target_z": 3.531249743640891, "ce": 6.205295085906982, "genuineness": 3.8797430992126465, "identity": 0.6137290000915527, "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_Astonishment_Surprise/21aa3ea37eb3a1d54b5164486a325f796289e76bb6429e8a22686c492e548f12.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "2302093e188175b1bdd903abc08e68f3e977f2f293da3e10af4146169d170d80", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0da9aced9ab7f06bed7e68b1f5a149087c415ee2edd0f8d0427bbe9204b3e50f", "generation_seconds_batch": 20.32065028010402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7458372116088867, "target_z": 0.8476562516865731, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.2640325129032135, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2302093e188175b1bdd903abc08e68f3e977f2f293da3e10af4146169d170d80.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "234456df9cc2753e289af3e70301ce1fc7bec7780b956958cb2746e451538901", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ff58eee92c4fc6f9568c8e38c2fc26d0043869c8255c177086a26c876425203a", "generation_seconds_batch": 22.50033313105814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1742258220911026, "target_z": -0.1875, "ce": 6.125868320465088, "genuineness": 3.785602569580078, "identity": 0.5326246023178101, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/234456df9cc2753e289af3e70301ce1fc7bec7780b956958cb2746e451538901.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "2344a28882ae01ef287bfa2aa1489fd306094757116571d566723cac07efe318", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2d97d1a58201b9237c5342d0b0afa4d276bedfff67731e2b61258f0cc91e99b5", "generation_seconds_batch": 22.406603661947884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.969728946685791, "target_z": 4.8749997841186445, "ce": 5.77639102935791, "genuineness": 4.15588903427124, "identity": 0.24844595789909363, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2344a28882ae01ef287bfa2aa1489fd306094757116571d566723cac07efe318.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": "2347c726b697eeb6e65bcfbebf31df7cde3b01d6625cffc31c7f16d47567ecbe", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e9bdf428ed64ac4d7deaaf2492b52f124dbddc97b06bc2e3ab3321bc56161a08", "generation_seconds_batch": 14.086121891974472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.184572219848633, "target_z": 3.4531248718204455, "ce": 5.927301406860352, "genuineness": 4.143336772918701, "identity": 0.46587079763412476, "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_Astonishment_Surprise/2347c726b697eeb6e65bcfbebf31df7cde3b01d6625cffc31c7f16d47567ecbe.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "23cb1dc3a0b628af120263cc02a5c01e64eee55d75e1378c41ff0111df7ac586", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb7b29e9ffae8d35d7fcb0a6ec22b977eddc91b652a29d50438911c33355b711", "generation_seconds_batch": 21.41557782597374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7186551094055176, "target_z": 2.6093750472240465, "ce": 6.070269584655762, "genuineness": 4.042920112609863, "identity": 0.5266112685203552, "hypothesis": "The door is still open. I put your coat on the chair Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/23cb1dc3a0b628af120263cc02a5c01e64eee55d75e1378c41ff0111df7ac586.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "24b5751f4eda3573ded730e1765985704f2f79453816ff0aedc08b7c1fa61b3f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "01f37c76b2f2f6f7551ca9a3fe39a5c00bab82b1845b1b656df422c1552c0879", "generation_seconds_batch": 20.384269289905205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0810351371765137, "target_z": 3.2656250067462924, "ce": 6.149696350097656, "genuineness": 4.3504462242126465, "identity": 0.518208384513855, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/24b5751f4eda3573ded730e1765985704f2f79453816ff0aedc08b7c1fa61b3f.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "2578ddd332a867637cdd5b899771bd62f38941b07137a0526d06872e418e1c5c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ae36f3f877caa258f5d8dc47a1b7d2f824e1f3c173cdb8936e218e323ca5b37a", "generation_seconds_batch": 21.80989245302044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3088204860687256, "target_z": 1.8671874696416844, "ce": 5.8875885009765625, "genuineness": 4.005263805389404, "identity": 0.5582566857337952, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2578ddd332a867637cdd5b899771bd62f38941b07137a0526d06872e418e1c5c.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "25d1ee878dbdae24177d21cf8368bec9ec0987e09000b8d8ea1e77f201c4bb6f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "638b6042c7df853a27408a5fff334caef5ad847c4ef0b4b9c489b837d23a0fe1", "generation_seconds_batch": 21.771616299985908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 5.959072113037109, "genuineness": 4.068024158477783, "identity": 0.33322083950042725, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/25d1ee878dbdae24177d21cf8368bec9ec0987e09000b8d8ea1e77f201c4bb6f.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "260e47573d7a73d0dd1d8ef08bf642f3d30c8d8e40e590b53666cdd1332aad11", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ed5b814d94af9b549bcefeb62d6f5687dd1263224de5bfa4add4b88d220044b7", "generation_seconds_batch": 22.14605030894745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5383241176605225, "target_z": 4.093749770626061, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.3061053156852722, "hypothesis": "I found the little box. It was beside the old w 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_Astonishment_Surprise/260e47573d7a73d0dd1d8ef08bf642f3d30c8d8e40e590b53666cdd1332aad11.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "266b369aa44687e1ad7f31afec38fb8acf76a5545537c5119c23be3f8bea1ebd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bb7b95e91ac37cd7e2e9b1304dea69b4bb8c0a1102d66d43ba377bdbf2af7098", "generation_seconds_batch": 20.146875887992792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.985266923904419, "target_z": 1.2812500674629235, "ce": 6.141753673553467, "genuineness": 3.9801597595214844, "identity": 0.8271963596343994, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/266b369aa44687e1ad7f31afec38fb8acf76a5545537c5119c23be3f8bea1ebd.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": "26b52e4690ff0f208ec89723f16bbe48522aa8c47fe3fd288d34f7895e108c49", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae2d76fcd16c22e40de4b0e473bd8b5600ce1d56d1d8fb276c2c3cbb7d965912", "generation_seconds_batch": 19.41039783100132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.952472686767578, "target_z": 4.843749662685383, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.644497275352478, "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_Astonishment_Surprise/26b52e4690ff0f208ec89723f16bbe48522aa8c47fe3fd288d34f7895e108c49.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "0ac8d448c928d4b79a68e640b50ee188592f40465e778b97afcd6c9a52eb6a42", "generation_seconds_batch": 14.727747478988022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13539938628673553, "target_z": -0.25781250337314615, "ce": 6.372091293334961, "genuineness": 4.293961524963379, "identity": 0.28699570894241333, "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_Astonishment_Surprise/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "26f72d03a2f84c041471146c6884e457c2697ed320cece68ec6a97b546b71b44", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e13361575c4000811bc3dd8395c9e5b71ba809483bdd21fda4fbaca9d0c0501", "generation_seconds_batch": 17.52603340893984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3571341037750244, "target_z": 3.7656247908649374, "ce": 6.24500846862793, "genuineness": 4.425758361816406, "identity": 0.23128610849380493, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/26f72d03a2f84c041471146c6884e457c2697ed320cece68ec6a97b546b71b44.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "271475665a7a5581d17ded904d6bdb9f23e4af66010ef8fc330bc620ca29c5b2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f518126c7427ebf1e758f186a7ce2e4bb07d97d264db17a4d9024f334c626947", "generation_seconds_batch": 22.952403683098964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6772329807281494, "target_z": 6.156250013492585, "ce": 5.8875885009765625, "genuineness": 3.660081624984741, "identity": 0.20497900247573853, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/271475665a7a5581d17ded904d6bdb9f23e4af66010ef8fc330bc620ca29c5b2.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "272deb4ca7489ec9238200c605d187a58e9bee05938186b785e406b8c55c5918", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eca0b1272824935532f784fc9fc4f3fa2528e42ce45288358a504572be5fbf3e", "generation_seconds_batch": 21.318034525960684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.969728946685791, "target_z": 4.8749997841186445, "ce": 5.752562999725342, "genuineness": 3.948779582977295, "identity": 0.28830623626708984, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/272deb4ca7489ec9238200c605d187a58e9bee05938186b785e406b8c55c5918.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "2736570b3a465296024964b66fba1493c5e3321887f239b3d1e80c3f33a836ae", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1e7ee5f132068ed1c70a72cfa4d4dba14e5f094bb35459eb749626598f04a88", "generation_seconds_batch": 20.435606669052504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4183900356292725, "target_z": 5.687499919044492, "ce": 5.990842819213867, "genuineness": 3.9676074981689453, "identity": 0.38223713636398315, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2736570b3a465296024964b66fba1493c5e3321887f239b3d1e80c3f33a836ae.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "27392ac0ce0060c717e46faa9679c0833158a33d020ef302d8784bd6ea72dc6f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "db68cb1a35e1f30498e59d4fb99c1ef848aae43acf8c8bbfa6835ba52aa8da61", "generation_seconds_batch": 22.853345884010196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1019655168056488, "target_z": -0.3183593707835673, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.679990291595459, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/27392ac0ce0060c717e46faa9679c0833158a33d020ef302d8784bd6ea72dc6f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "274938b31e24155673919f004d2a4aacb30b7ebc23d0dcfce0acb635141dca44", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e63af708ebf93dbbf8abda966d57aac003ff9a1f0645c8f05d9c7c36337fea25", "generation_seconds_batch": 15.790743842022493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05451098084449768, "target_z": -0.4042968809030058, "ce": 6.022613525390625, "genuineness": 4.319066047668457, "identity": 0.7362297773361206, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/274938b31e24155673919f004d2a4aacb30b7ebc23d0dcfce0acb635141dca44.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "276c4d5307df5b346626ebaee9bfd8fcf634ec5b74458162101cd0203ab692e4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6a64e0d3f05d745ec4baa41ea3a05ee6aaede62faac2c494f65bd9647de950b4", "generation_seconds_batch": 22.20311053597834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9516136646270752, "target_z": 3.031249959522246, "ce": 5.673136234283447, "genuineness": 4.168440818786621, "identity": 0.5460864305496216, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/276c4d5307df5b346626ebaee9bfd8fcf634ec5b74458162101cd0203ab692e4.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "2811f1a13ae4098b53890a9a973f617798873ba6ce8858bad208d0d3515f5a4a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0d4d7d67edf6b1a675f6d15eecf8fa3e82c305eb2fdc88a8c013d2140b3f14ec", "generation_seconds_batch": 15.7211341150105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12677128612995148, "target_z": -0.2734375101194385, "ce": 6.2767791748046875, "genuineness": 3.9048471450805664, "identity": 0.399853378534317, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2811f1a13ae4098b53890a9a973f617798873ba6ce8858bad208d0d3515f5a4a.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "2814189afc56023356637cd613843215db0074849886b71b80c8ab5bde7205f3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7114c8fa9867cb37c74ddfc68507d6689e7e54d1eaea4d79ff5d854683854621", "generation_seconds_batch": 23.233206520904787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4347870349884033, "target_z": 3.906249905551907, "ce": 6.125868320465088, "genuineness": 3.9927117824554443, "identity": 0.6169074177742004, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2814189afc56023356637cd613843215db0074849886b71b80c8ab5bde7205f3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "282735165b8c85d54fb7108e7dd58f6f586a1401ef05036ee1d071b5b9067f97", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "06e3c90712aa7b3ede53db9ea75121cd25c8d23eb4339c5b43f277b9723a9914", "generation_seconds_batch": 17.134250031085685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2630841732025146, "target_z": 5.4062496896705525, "ce": 6.1020402908325195, "genuineness": 4.017816066741943, "identity": 0.15464703738689423, "hypothesis": "Ik 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_Astonishment_Surprise/282735165b8c85d54fb7108e7dd58f6f586a1401ef05036ee1d071b5b9067f97.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "287b87e7b2eb663f17496af375e8deee59227a1c3c30d2ea51ab2abc22caf995", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "77c0b5f226c77e623ac12ca6e532d47b80a7909ffe2741d81bbaf89ea6ae0333", "generation_seconds_batch": 19.224119522958063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.867051124572754, "target_z": 6.500000053970338, "ce": 5.673136234283447, "genuineness": 3.8671910762786865, "identity": 0.5983766317367554, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/287b87e7b2eb663f17496af375e8deee59227a1c3c30d2ea51ab2abc22caf995.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "28b14adad380e2d72eae81671be74b3c632f18b76d771e9b3586ea41651b97ad", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b9f29d079870e7499446f4bca2aaff1131549b24668e8543ccec142c063e9a6f", "generation_seconds_batch": 24.159047969034873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2734489440917969, "target_z": -0.00781247638797679, "ce": 6.24500846862793, "genuineness": 4.413206577301025, "identity": 0.47829586267471313, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/28b14adad380e2d72eae81671be74b3c632f18b76d771e9b3586ea41651b97ad.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "2920c729b706ec06d5e2fc0dd9408abb32863c757467c138311ccbd54605d17f", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2ed5b6211738070acbef8359349f4d4c35f52d2478f8e01901df1a0f5791d9a1", "generation_seconds_batch": 14.066625809995458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08039526641368866, "target_z": -0.35742188764929816, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.46748870611190796, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2920c729b706ec06d5e2fc0dd9408abb32863c757467c138311ccbd54605d17f.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": "2ab5862523128321e3e499c900abd89ea96255652738590d3bf798db4c090f3c", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b06b6cb524275cbe2505c8cce0981db70fe3a52dfeafe5b3db260882de5ae0b", "generation_seconds_batch": 23.647055542096496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2556534707546234, "target_z": -0.04003908316052031, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.7082980275154114, "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_Astonishment_Surprise/2ab5862523128321e3e499c900abd89ea96255652738590d3bf798db4c090f3c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "2b284f2c3726f91833e1737b238ed21a5db6b788f3f2a53ba12ced1ab651d098", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0a93211abeaf8e3981ad4642554335f603e39d2aa6b95b05e47e60fb4ea26265", "generation_seconds_batch": 23.305688870023005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06961014866828918, "target_z": -0.3769531325895789, "ce": 6.141753673553467, "genuineness": 4.293961524963379, "identity": 0.7366924285888672, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2b284f2c3726f91833e1737b238ed21a5db6b788f3f2a53ba12ced1ab651d098.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "2b3fe4bbffe06a14dd61633b262a6c1550d64f14f30ec47d3e790469e6ce45d7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b83fee92d4df5c04e5ed5d24ffb93b907eb303bb067daf5bf338429a4271d5e3", "generation_seconds_batch": 23.586476730997674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9352166652679443, "target_z": 4.81249997301483, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.5997647047042847, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2b3fe4bbffe06a14dd61633b262a6c1550d64f14f30ec47d3e790469e6ce45d7.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "2b46fd69d84d08a52c4154a64d48165a1c5ef365e03fc8fd7c0df1eb7abf61ee", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f33c15360e71933dce9e05e07026bcb2660f5b8d5f9f76a01caa0b1d95ef3f5f", "generation_seconds_batch": 23.598710079095326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.726423978805542, "target_z": 0.8124999730148306, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6482880115509033, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2b46fd69d84d08a52c4154a64d48165a1c5ef365e03fc8fd7c0df1eb7abf61ee.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "2b55a166a11afdd15ee90a030109cd8f300033c3757b3f08784d69be23135e56", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a03f4055a835e47e82bf3540b38efd49480c140568d3724749817e8f6477511b", "generation_seconds_batch": 15.933126776013523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0724070072174072, "target_z": 3.249999946029661, "ce": 5.911416053771973, "genuineness": 3.9425034523010254, "identity": 0.39617717266082764, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2b55a166a11afdd15ee90a030109cd8f300033c3757b3f08784d69be23135e56.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "2bb231c4446f5836e19f5b80b4893528eda90c2bad84ce01dfd6adbe9ed09b60", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "92b29ba193792566c1bf25c3dbd730d8298aaf28e4d068adce33797a29dc0e8e", "generation_seconds_batch": 16.67886730399914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029266595840454, "target_z": 3.1718750742092157, "ce": 6.24500846862793, "genuineness": 4.356721878051758, "identity": 0.6173450946807861, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2bb231c4446f5836e19f5b80b4893528eda90c2bad84ce01dfd6adbe9ed09b60.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "2c1913f0e182e7030baf60ccaf1d7c527059c499ce5a232fc34764b025abe7ef", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6ff5b41227d8580b72745359b2f4eb5d75efcbb34452e1e14d0b884e072f6500", "generation_seconds_batch": 15.525128332083113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0378947257995605, "target_z": 3.187500134925847, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.42440271377563477, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2c1913f0e182e7030baf60ccaf1d7c527059c499ce5a232fc34764b025abe7ef.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "2cc9f1a61cb7eedc53c9c1dbc0001bcc0852cbddd7e56ee29a7cef819549fd38", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a5fe120a5c6c6214aea5c515f466f0e6bb25de32109a88843487f90cc36d8648", "generation_seconds_batch": 21.53679089504294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3735312223434448, "target_z": 1.9843749932537076, "ce": 5.879645347595215, "genuineness": 4.281409740447998, "identity": 0.4375574290752411, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2cc9f1a61cb7eedc53c9c1dbc0001bcc0852cbddd7e56ee29a7cef819549fd38.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "2cf480ff91237bd0b9fab5dc48bd33ec41df1d3a6e603ac04bb8e0ac71c0a6fd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "655755355acdddfdd9f0984ee5dccbca0e7169bbb0afe18d5ed828657fa6e40a", "generation_seconds_batch": 21.299519303953275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8429032564163208, "target_z": 1.0234374291639303, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.732338547706604, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2cf480ff91237bd0b9fab5dc48bd33ec41df1d3a6e603ac04bb8e0ac71c0a6fd.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "2d3a2dafd966de200f3a93de356a397d17bcdacc78deb4170b125189dbc1b390", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0a2dd09e900469bf9a46ed78c92be8d58edaa7907d96c47386f6e4ac4f7e1da0", "generation_seconds_batch": 23.461217516916804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5495480298995972, "target_z": 0.4921875236120232, "ce": 6.141753673553467, "genuineness": 4.093128204345703, "identity": 0.4076387584209442, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2d3a2dafd966de200f3a93de356a397d17bcdacc78deb4170b125189dbc1b390.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": "2d7851fe3b15245d039ef6c2cf37afac410f9a5774dc2c750914c3ea17e8d844", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6900a0c458dad5e163279b16aaa5edbea812ab6643d21dffdc03d11029509272", "generation_seconds_batch": 15.314109888044186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2622251510620117, "target_z": 3.593749986507415, "ce": 6.046441555023193, "genuineness": 4.218649387359619, "identity": 0.7509693503379822, "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_Astonishment_Surprise/2d7851fe3b15245d039ef6c2cf37afac410f9a5774dc2c750914c3ea17e8d844.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "2da7cc9375dcd251e1a4c4ec940872f8e09f2920e395b2cd7fb7a9ff5ba7be4e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "837c41745d0f605460c6f68ae699bb0f441b6a57eed53402a6c9fba7375402fb", "generation_seconds_batch": 20.354350549983792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17260804772377014, "target_z": -0.19042969888436834, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.6679298281669617, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2da7cc9375dcd251e1a4c4ec940872f8e09f2920e395b2cd7fb7a9ff5ba7be4e.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "2e80441c0bb5c1b26f880dcb4462d4877bf7558b23969f08a1d107a87d6646bb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4ad54d9e7502a5eca91b1b672d02b4b0e5137822fbc98e29da6ee627ed6d22f6", "generation_seconds_batch": 22.8259565429762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7013989686965942, "target_z": 2.5781251416721394, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.6150795221328735, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2e80441c0bb5c1b26f880dcb4462d4877bf7558b23969f08a1d107a87d6646bb.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "2efed22e41d2529ad3e366e6b2e4633c53adf371db29094000731427c4adb15e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1c0a5f503c9abf8ea438d5fe36400f86ec097e6f50b17c1b3a7184526aa766b7", "generation_seconds_batch": 15.773435486014932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7393661737442017, "target_z": 0.8359375640897773, "ce": 6.173524379730225, "genuineness": 4.68307638168335, "identity": 0.4822154939174652, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2efed22e41d2529ad3e366e6b2e4633c53adf371db29094000731427c4adb15e.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "2fef8a4e8ec8ba3bcd72614c193f09199a9453952e5fae23bbaca09b2a91645d", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fe1f3f5c631f91c4eacad4ca34057991722a0e39295d3e58b7f2cc9fd4d9dd77", "generation_seconds_batch": 15.525128332083113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0542916059494019, "target_z": 1.406249905551907, "ce": 6.403861999511719, "genuineness": 4.457139015197754, "identity": 0.3467346727848053, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/2fef8a4e8ec8ba3bcd72614c193f09199a9453952e5fae23bbaca09b2a91645d.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "309403ac68dc4528d2588f6bb86d7b842aab4f0b46deed81de4c3d8fe98c1b5c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "998d97b4dba29e964e35fec54d5093409a04f586967b9b692b75c4d4c1c89f42", "generation_seconds_batch": 21.099196358933114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4002745151519775, "target_z": 3.843749662685383, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.41793403029441833, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/309403ac68dc4528d2588f6bb86d7b842aab4f0b46deed81de4c3d8fe98c1b5c.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "30a4aab5ee5b27f4dd310752c4279166941687db9d6084fd975ecb4ab2a1d7e3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af4418beda487f6735d6a8a5fce170513cea958967c4df7425eb8d8d6bba964a", "generation_seconds_batch": 24.363525978988037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227712631225586, "target_z": 3.531249743640891, "ce": 6.205295085906982, "genuineness": 4.162164688110352, "identity": 0.43806278705596924, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/30a4aab5ee5b27f4dd310752c4279166941687db9d6084fd975ecb4ab2a1d7e3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "311d50de7058dd714c2b663ccaf1ef8f9d6b8db6cb7950d3b81925c0c1232f2b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93878fc348483ffeaea6ef5bea9d6ad3268e411ac468c250f7f00ad28043ade0", "generation_seconds_batch": 19.921061204047874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.22943115234375, "target_z": 7.156250013492585, "ce": 5.77639102935791, "genuineness": 3.6663577556610107, "identity": -0.022871751338243484, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/311d50de7058dd714c2b663ccaf1ef8f9d6b8db6cb7950d3b81925c0c1232f2b.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "3270b194e886f5b0251bf758a4045a096d44bc19bc51ef1ee7f89abe9aab45d2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9ce6fcccc70fae5f467344dc106f9438d0f814f84c5752dfb12668481ce0a07a", "generation_seconds_batch": 14.767227896954864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7307380437850952, "target_z": 0.8203125033731462, "ce": 5.982900142669678, "genuineness": 4.3504462242126465, "identity": 0.6547215580940247, "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_Astonishment_Surprise/3270b194e886f5b0251bf758a4045a096d44bc19bc51ef1ee7f89abe9aab45d2.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": "33911af638b32c948950c57cf370e9e5bbd57e1693e203d94a4202bc252df253", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdb68b311ed96211bd060c80c9e32f194d03925e62a4b8feec166df44f8e8e68", "generation_seconds_batch": 22.662932388018817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.107778549194336, "target_z": 5.124999892059322, "ce": 5.967014789581299, "genuineness": 4.055472373962402, "identity": 0.36999282240867615, "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_Astonishment_Surprise/33911af638b32c948950c57cf370e9e5bbd57e1693e203d94a4202bc252df253.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "33d408a5fe05ba8133e55f437a833b6768cf82b1641eae19768a2a4abe9f98d8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f36c1ba241e1092f8536e93e7292cfc32c5f6eee0d17af4e712ddca69914d7df", "generation_seconds_batch": 23.105600110953674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35541585087776184, "target_z": 0.14062500674629236, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.500201940536499, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/33d408a5fe05ba8133e55f437a833b6768cf82b1641eae19768a2a4abe9f98d8.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "ea74aca6b2bc5ebb11896a3f3c338a7ecdcd6de0f5d321af8efd43365ecc1b7e", "generation_seconds_batch": 17.719664336997084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5409198999404907, "target_z": 0.4765624628953921, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7189235687255859, "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_Astonishment_Surprise/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "343fd00825ed53cbef7aafca06995f8fb7c1553c01bca96ef08689eaf405af46", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "282eca3c5304522e2a97e655137d4e21a9f7f35cef4ffef5f2c936036888f8d1", "generation_seconds_batch": 16.29615479707718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.848935604095459, "target_z": 4.656249797611229, "ce": 5.982900142669678, "genuineness": 3.873466968536377, "identity": 0.561345100402832, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/343fd00825ed53cbef7aafca06995f8fb7c1553c01bca96ef08689eaf405af46.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "3e77a157f36c0f40ccb49acd4d3ce97efb100ec47a3827b65479414c6f93f1a0", "generation_seconds_batch": 16.912360265967436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06206056475639343, "target_z": -0.39062500674629236, "ce": 6.459460258483887, "genuineness": 4.080576419830322, "identity": 0.30606234073638916, "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_Astonishment_Surprise/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "34c9979d562eea6d0c5a298a06ff80f46bef8b50aea8e43b4d9a16f8f376c6a9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fa612fd60ddd2b827ed802204e896a8593bfc44ba6827722e947ca6b58415923", "generation_seconds_batch": 22.387362741981633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9516136646270752, "target_z": 3.031249959522246, "ce": 6.348263263702393, "genuineness": 4.042920112609863, "identity": 0.3146187663078308, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/34c9979d562eea6d0c5a298a06ff80f46bef8b50aea8e43b4d9a16f8f376c6a9.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "34ea462259c18b002970753dfbd56ce918f6d817424fd07d7d1974c2bf506714", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "239a0ca036e94d058b7defaaaa79fdf509ddfa60614cd9ccc80f5d3f103df068", "generation_seconds_batch": 23.474562064977363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8567047119140625, "target_z": 2.8593751551647237, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.42164185643196106, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/34ea462259c18b002970753dfbd56ce918f6d817424fd07d7d1974c2bf506714.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "355fd513fddda06d28dafe3f698cba5b75864c380b57f0324b0e53217f3fdbd7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96ba5488eceab6034195e411341b01e7e621d320dc2884f0c35d7127b2f78d46", "generation_seconds_batch": 19.921061204047874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.831679344177246, "target_z": 4.624999676177968, "ce": 5.764476776123047, "genuineness": 3.911123275756836, "identity": 0.25223541259765625, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/355fd513fddda06d28dafe3f698cba5b75864c380b57f0324b0e53217f3fdbd7.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "35ae3854693b1755452649926f9c4555a750d4e396afd5c7d9b5ca4fa27f3bd4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9771d7691a1622b2cf7842e002d017efc12a4e17ed6f2e38a9450c1f8c1c09e0", "generation_seconds_batch": 22.86378760403022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2513394355773926, "target_z": -0.0478515595484971, "ce": 6.078212261199951, "genuineness": 3.9550557136535645, "identity": 0.3539782762527466, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/35ae3854693b1755452649926f9c4555a750d4e396afd5c7d9b5ca4fa27f3bd4.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": "3620ec57860890a6857e41b245c511928f47e690d333f178929f96e5177a1655", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fb560e3a23c586a3c5bea5878ed50fc6e881c8315573de7c154b2f3b5e95c4d", "generation_seconds_batch": 23.041800025035627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9343575239181519, "target_z": 3.000000053970339, "ce": 6.24500846862793, "genuineness": 4.093128204345703, "identity": 0.6118035316467285, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3620ec57860890a6857e41b245c511928f47e690d333f178929f96e5177a1655.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "363d98610336e38ff4acb63715e1682576417ff3dd7405d2487d99a82c97611e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e95d4d9b0e0b3e40350e0cd3feb6834ea49c3ef8bc3b2e3d2509d35f335814e", "generation_seconds_batch": 23.83226701593958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4425560235977173, "target_z": 2.1093750472240465, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.6205625534057617, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/363d98610336e38ff4acb63715e1682576417ff3dd7405d2487d99a82c97611e.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "36786c5cca0ad73312d029ce2d7d68b44bd811596de4360183ca78a567b06fa6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3d8fa78cd2ccec9b22763808748274d0b9f5e8b410d9bd06dc8b95dc874ff9c7", "generation_seconds_batch": 23.29516900505405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.796307921409607, "target_z": 2.749999946029661, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.7379188537597656, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/36786c5cca0ad73312d029ce2d7d68b44bd811596de4360183ca78a567b06fa6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "36c159736ce415f8577bad167b5ba31271bbef967d67c1eedba0a0e0944a6337", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d2188d6ded2d3e25182d9d6795f4f406eb5ac9134b9e3b19cb525e5fec7f9fb1", "generation_seconds_batch": 22.04606025700923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1149076521396637, "target_z": -0.29492188764929816, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.674842119216919, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/36c159736ce415f8577bad167b5ba31271bbef967d67c1eedba0a0e0944a6337.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "36dab9cd6b17e333e2d0956300e05ec82779919e29fa0f92a0e0d6c0f7eec53f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "56d1e40b32d35e0313db911541890c0feb6cb47a45e8e6a2bee0119dca206c42", "generation_seconds_batch": 20.952991814003326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24972166121006012, "target_z": -0.050781258432865434, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.6179112792015076, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/36dab9cd6b17e333e2d0956300e05ec82779919e29fa0f92a0e0d6c0f7eec53f.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "37b61101f6b85e775014efcaf9a7f1423895b1062e6de66a538a9c418ae82666", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6021280a3806fc330cd9ec8697d498bb9f25fc285f65946c980ff2fd68abca6d", "generation_seconds_batch": 22.53617779398337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8385891914367676, "target_z": 1.015624898805615, "ce": 6.149696350097656, "genuineness": 3.973883628845215, "identity": 0.43848660588264465, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/37b61101f6b85e775014efcaf9a7f1423895b1062e6de66a538a9c418ae82666.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "37d5b81842dd0980d3ab6698ef21fabaffc6b4b6702bddeb46dfc0f066f74141", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c665bedad7f815f106a2bf72974708073330dbafbd2d250fb3d169a21c63847c", "generation_seconds_batch": 22.895109678036533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.136258602142334, "target_z": 1.5546875505971927, "ce": 6.141753673553467, "genuineness": 4.595211505889893, "identity": 0.628673255443573, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/37d5b81842dd0980d3ab6698ef21fabaffc6b4b6702bddeb46dfc0f066f74141.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "383fba148c0ac51039a336f854e896379aca3e501dc8f98615bc56bdd7ba646f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a9a7eb732ad04f4341eab28a52c64d3b4f7289e9c57afdcc52eb6dd72cfa7fa2", "generation_seconds_batch": 13.844546045991592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6151179075241089, "target_z": 2.4218749662685384, "ce": 6.372091293334961, "genuineness": 4.21237325668335, "identity": 0.38406771421432495, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/383fba148c0ac51039a336f854e896379aca3e501dc8f98615bc56bdd7ba646f.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "38479793e5d5d2d604fe043de7b1285f05ebc3939f70c03805b68d6437647b63", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a30181a4a82009a56203d57f7bec5d553d3cc2f5b9c14f3c2df7c0f7b39e3d43", "generation_seconds_batch": 21.732644452014938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9774980545043945, "target_z": 3.0781251416721394, "ce": 6.340320587158203, "genuineness": 4.337893962860107, "identity": 0.503351092338562, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/38479793e5d5d2d604fe043de7b1285f05ebc3939f70c03805b68d6437647b63.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "3866e4339b01ea6a6fd7c746100ff772d3af223b6bd528ca36e3afc72f09e5cc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "08f5cc6251ec63336a6bc29ff4bd771366a48e9c3077bcf793d95f56d15730dc", "generation_seconds_batch": 22.65557683899533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.245828151702881, "target_z": 5.375, "ce": 5.959072113037109, "genuineness": 3.9299514293670654, "identity": 0.4421330690383911, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3866e4339b01ea6a6fd7c746100ff772d3af223b6bd528ca36e3afc72f09e5cc.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "38ef23fdd9ffa8645580e4377e5430cc77d1be584cb0e90e31e5f08f602ef5c5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bd972085a169878999050e6d2e43c2acef9d3e0e05707fa87a845449152632f", "generation_seconds_batch": 23.181026563979685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.244968891143799, "target_z": 3.562499865074153, "ce": 6.086154937744141, "genuineness": 4.105680465698242, "identity": 0.7481905221939087, "hypothesis": "J'ai trouvé la petite boîte. Elle était près, de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/38ef23fdd9ffa8645580e4377e5430cc77d1be584cb0e90e31e5f08f602ef5c5.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "391536f9bbb60e8a9ffe0ff421f9b2e4a8496ef9f3572b7a095be2871e566f80", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5887887f8bf4ac5949c2af5a0de427b89eba32524fe137157d135be6587d2ac7", "generation_seconds_batch": 21.51751635200344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.004241466522217, "target_z": 4.93750002698517, "ce": 6.078212261199951, "genuineness": 4.005263805389404, "identity": 0.5166270136833191, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/391536f9bbb60e8a9ffe0ff421f9b2e4a8496ef9f3572b7a095be2871e566f80.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "392a8d75a854ade33db797e8e1399d742e22287d667f1d8939bbfca33f997b98", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "259505c7802681c2212bd2a6114f80637e8a814c2529de97c485c35d858c5975", "generation_seconds_batch": 22.086081599001773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6591174602508545, "target_z": 4.312499757133476, "ce": 5.990842819213867, "genuineness": 4.162164688110352, "identity": 0.6100577116012573, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/392a8d75a854ade33db797e8e1399d742e22287d667f1d8939bbfca33f997b98.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "393a06eec7244572708cbbb4b4c81a451d4e9fe7b37e6f69d65a331f1aad257d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "625f74c5b17ac4b105c3969752ac1a80b75f51070fd690297f7afb116eb81e19", "generation_seconds_batch": 17.695559209096245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.184572219848633, "target_z": 3.4531248718204455, "ce": 6.316492557525635, "genuineness": 4.18099308013916, "identity": 0.6117737293243408, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/393a06eec7244572708cbbb4b4c81a451d4e9fe7b37e6f69d65a331f1aad257d.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "396359461f2506bd693accf42384d2c0d37bd900e13be84da8e690360c6f19ed", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "02f97ee4c208232f60a921db9569c37ffda60e27e1b0acb937a0cc13c4ce4cb7", "generation_seconds_batch": 17.08570898498874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3562750816345215, "target_z": 1.9531250877018005, "ce": 6.3641486167907715, "genuineness": 4.256305694580078, "identity": 0.5792485475540161, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/396359461f2506bd693accf42384d2c0d37bd900e13be84da8e690360c6f19ed.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "398d153d004c64317539f14ff2d8f716c2f69451c704eff3b81cfd5b53acce89", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d6b844eee0597b49abf76d5d6630f9da602f75e7f6311d1947913b667db5731a", "generation_seconds_batch": 21.62604217894841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5797463655471802, "target_z": 0.546875020238877, "ce": 6.1020402908325195, "genuineness": 4.469690799713135, "identity": 0.370248019695282, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/398d153d004c64317539f14ff2d8f716c2f69451c704eff3b81cfd5b53acce89.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "3b5b5cfbe3c6ee871ac19fb1822a2ac23fec7d6e2365f375b19be6bcca101ed6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7cb2e4b291c730e3cf0ed489edafd51e045394e46822178282384feb47ffa219", "generation_seconds_batch": 24.37243606999982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8308203220367432, "target_z": 2.812499973014831, "ce": 6.006728172302246, "genuineness": 4.168440818786621, "identity": 0.6804822683334351, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3b5b5cfbe3c6ee871ac19fb1822a2ac23fec7d6e2365f375b19be6bcca101ed6.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "3ba72c0b778392ebd9b701c8161fd432794370f3fae9ed778b0a57602478768a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0e3f803aa04b2b29deceb058a9cb65eca96f4dab2f1e053aa40c958f689b1a35", "generation_seconds_batch": 20.796021185000427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0672338008880615, "target_z": 1.4296874966268538, "ce": 6.165581703186035, "genuineness": 4.2374773025512695, "identity": 0.6898453831672668, "hypothesis": "de deur staat nog open ik heb je jas op de stoel gelegd zeg maar wanneer je klaar bent", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3ba72c0b778392ebd9b701c8161fd432794370f3fae9ed778b0a57602478768a.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "ad0b107af77d50a374476a13a7827b2fc680cf407e27ffd49fc678dbd6da1a0d", "generation_seconds_batch": 16.934857374057174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0931180715560913, "target_z": 1.4765624628953922, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.7928682565689087, "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_Astonishment_Surprise/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "3cbe134c3070c699c8377dfa714fc8b5bd3070b0da84429aa26ebe8937a4c273", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "77322c3cc4665317c5b2d2786617f8763c25bd191774371d3ee95d6b180e6ca2", "generation_seconds_batch": 20.63235355296638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5905314683914185, "target_z": 0.5664062381939884, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.45625022053718567, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3cbe134c3070c699c8377dfa714fc8b5bd3070b0da84429aa26ebe8937a4c273.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "3d040387a782c76b537a6d74f3c6aba52547abe2d1e2c5e986acc8776a592344", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "46f5c866155bb6676cc88c98bf185ac940d698c002360aae64eb726cc5316755", "generation_seconds_batch": 17.742100927978754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8903578519821167, "target_z": 1.1093750472240465, "ce": 6.070269584655762, "genuineness": 4.218649387359619, "identity": 0.5138278603553772, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3d040387a782c76b537a6d74f3c6aba52547abe2d1e2c5e986acc8776a592344.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "3d6bb2c97c38c620db743370b2ff26d3eaf0241a69eddd06e0e31210b72c6312", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aac5d91b914dc37becc0093fde9f71aae1212b84aaf74c303528eb2df6e2f566", "generation_seconds_batch": 20.761532320058905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5046708583831787, "target_z": 5.843749662685383, "ce": 5.863759994506836, "genuineness": 3.7793264389038086, "identity": 0.4680868983268738, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3d6bb2c97c38c620db743370b2ff26d3eaf0241a69eddd06e0e31210b72c6312.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "3d8d483d0438c0a26b1529564dead2f00c713e084347593b75312d40389ff2ef", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d25c8aff3133d34edbabfaad6335bfc6cba42b6dddf0b6b88a2c31a4e8c30557", "generation_seconds_batch": 19.531220534001477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6272008419036865, "target_z": 0.632812422417638, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.6038377285003662, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3d8d483d0438c0a26b1529564dead2f00c713e084347593b75312d40389ff2ef.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "3d9743819279f4baa7289f463f668f2e5e850c4c4a759321ac98aa464e2de28e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "01e17582ad0af328303ae7997faff7fbed7bc77e039851ed74a4451ee5f81f57", "generation_seconds_batch": 17.218848469899967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847217321395874, "target_z": 1.031249959522246, "ce": 6.1894097328186035, "genuineness": 4.362998008728027, "identity": 0.5977945327758789, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3d9743819279f4baa7289f463f668f2e5e850c4c4a759321ac98aa464e2de28e.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": "3de7e89e52cad547a5f51393c8a3c2d63ca49ffdf25403d2f8d640333239dbba", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "cad763ea04895065a3571e2c89858f11812369812b89e7e72421cd06bbf51775", "generation_seconds_batch": 23.29614661098458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947541952133179, "target_z": 3.1093750472240465, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.32320892810821533, "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_Astonishment_Surprise/3de7e89e52cad547a5f51393c8a3c2d63ca49ffdf25403d2f8d640333239dbba.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": "3dff6da0e0d07a88ef8a052c33223e16e4868934992337b19cf8eb7cdbce974c", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "527b29e3ecd89b4c547e9dd8ef4401d541b05c027ba645ab1e4aafd12d0c065a", "generation_seconds_batch": 22.744390050997026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2794811725616455, "target_z": 3.6249996761779673, "ce": 6.006728172302246, "genuineness": 4.262581825256348, "identity": 0.5403077602386475, "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_Astonishment_Surprise/3dff6da0e0d07a88ef8a052c33223e16e4868934992337b19cf8eb7cdbce974c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "3e101d50d4079c149f0e8c449a41c8a488d92178edfded5db14429e2177d821d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "11b50c298588d6a80d78657701a539202d83a57909dd82ec987ddb0fb6b31776", "generation_seconds_batch": 21.18676798196975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46929931640625, "target_z": 3.9687497166557213, "ce": 6.038498878479004, "genuineness": 4.13078498840332, "identity": 0.5004701614379883, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3e101d50d4079c149f0e8c449a41c8a488d92178edfded5db14429e2177d821d.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "3e2c158c39bcde4c4aa36419b86416654ed261625e5ba6f489145b28403f32bd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "19e85834332a38483d6bc24946e08d52b91e9d6a2a5679fcbc6977c4c877aa36", "generation_seconds_batch": 16.67886730399914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.287250280380249, "target_z": 1.8281250337314616, "ce": 6.395919322967529, "genuineness": 4.482243061065674, "identity": 0.4849189817905426, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3e2c158c39bcde4c4aa36419b86416654ed261625e5ba6f489145b28403f32bd.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "3eb00e61b4c1c389152fd8ae1a8f3d92e6c6d45577b55ed4f4bdf3d4cd68fa85", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "471e3c534d49c994a506cfee710d0a1b8c3f7012f5d803375ea621fc52f69e27", "generation_seconds_batch": 17.121350971981883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5115808248519897, "target_z": 2.2343751011943853, "ce": 6.173524379730225, "genuineness": 4.118232727050781, "identity": 0.5073850154876709, "hypothesis": "The 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_Astonishment_Surprise/3eb00e61b4c1c389152fd8ae1a8f3d92e6c6d45577b55ed4f4bdf3d4cd68fa85.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "3ef724f39c732de2ed0a26a8ebdc9668831523e67ef2a3ab51024db3dd1db35f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a1921ce4ceefc5c175a1da0791ba0cacdec5f03f5239294435d4368306a44177", "generation_seconds_batch": 16.10782462602947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.210456609725952, "target_z": 3.500000053970339, "ce": 6.086154937744141, "genuineness": 4.256305694580078, "identity": 0.33063116669654846, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3ef724f39c732de2ed0a26a8ebdc9668831523e67ef2a3ab51024db3dd1db35f.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "3f0ca8e5b25a39a3c95163c9815a5d25c42f3ecf7ed8fbd6ac174f9736f09bd2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9fd7e047c6565a6149a3887f3d8fc75b00caddfec03d5387799878f75e78e36e", "generation_seconds_batch": 21.36243586288765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2958784103393555, "target_z": 1.843750094448093, "ce": 5.816103935241699, "genuineness": 3.873466968536377, "identity": 0.4291711747646332, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3f0ca8e5b25a39a3c95163c9815a5d25c42f3ecf7ed8fbd6ac174f9736f09bd2.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "3f55deac0f00bc808819b30647dc8c3f189defb2d7c6cde627dbeaf7912f568e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2e27535b5ccb51a3ed82f619ef67e7e4eb0600aafb4678882fb6fb659ced42ee", "generation_seconds_batch": 19.40746266208589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9257293939590454, "target_z": 2.9843749932537076, "ce": 5.784333229064941, "genuineness": 3.8420867919921875, "identity": 0.5168654322624207, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3f55deac0f00bc808819b30647dc8c3f189defb2d7c6cde627dbeaf7912f568e.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "3f60f2589c89476cd78020d4d7ae36c04a948417692553eb7af0f4ecb50969e8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "56aee414cc03695a65759d050b03132b32fdf6ed74e5c95e70b7c6e8d719c0ce", "generation_seconds_batch": 22.895109678036533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5115808248519897, "target_z": 2.2343751011943853, "ce": 6.149696350097656, "genuineness": 4.406930446624756, "identity": 0.48736104369163513, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/3f60f2589c89476cd78020d4d7ae36c04a948417692553eb7af0f4ecb50969e8.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": "403a712a9ad925f5f9b41d6e7bca1a4d5f63acce21bed4fd97040927fd969bda", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "232eb41958b38b10695d248c19eaea008d429b78b863d3f4d2b9f2906e200780", "generation_seconds_batch": 23.085536765982397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6151179075241089, "target_z": 2.4218749662685384, "ce": 6.165581703186035, "genuineness": 4.168440818786621, "identity": 0.30034297704696655, "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_Astonishment_Surprise/403a712a9ad925f5f9b41d6e7bca1a4d5f63acce21bed4fd97040927fd969bda.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "418b77ea8cdcedf5c85855a6e988006637df1bc04340eb41dc04704c2e3259ec", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d0d0752c512b9ec4967f6d5656c8f4e8e2c16ab7c506fbd58a8ee2db00422ead", "generation_seconds_batch": 15.49550167308189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.366621494293213, "target_z": 5.593749986507415, "ce": 5.792276382446289, "genuineness": 3.773050308227539, "identity": 0.6091652512550354, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/418b77ea8cdcedf5c85855a6e988006637df1bc04340eb41dc04704c2e3259ec.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "427fdbffc51df99898aae3ac977d322021b47dd5c041f09d2aace3df02594955", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "63f097f867d30d3df8ff412a853dd76af87345d4518cdfcb13176e92a5ba02e1", "generation_seconds_batch": 21.510598473949358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6703413724899292, "target_z": 0.7109375101194385, "ce": 6.23706579208374, "genuineness": 4.143336772918701, "identity": 0.4269584119319916, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/427fdbffc51df99898aae3ac977d322021b47dd5c041f09d2aace3df02594955.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "4327655d26bbf040904233a7958d0d18f9712a410917c9e64d2341e7da6244f6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90a40b29c42516438678488cb67b9880cbde542bbed2ceccf2bd9306a09217f9", "generation_seconds_batch": 22.87108711397741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.696225643157959, "target_z": 0.7578124763879768, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.7738731503486633, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4327655d26bbf040904233a7958d0d18f9712a410917c9e64d2341e7da6244f6.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "fcc83db53f2708eadf54609ee33557b03734204ecad0f8f35ee9ed2878e1f53a", "generation_seconds_batch": 17.719664336997084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8234900236129761, "target_z": 0.9882811504921879, "ce": 6.221180438995361, "genuineness": 4.2751336097717285, "identity": 0.4940125644207001, "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_Astonishment_Surprise/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "438fa3a1bd71a65c7f5d238c0dff2e5ad0aec9a33e6145de26f333260b74f7f8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "645bff876985b1e51ee8588d8ad061dd8f1e3d694b6c0c2dc6b1c6d881388e57", "generation_seconds_batch": 19.41514660802204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2915643453598022, "target_z": 1.8359375640897773, "ce": 5.95112943649292, "genuineness": 3.810706615447998, "identity": 0.5975407361984253, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/438fa3a1bd71a65c7f5d238c0dff2e5ad0aec9a33e6145de26f333260b74f7f8.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "439a1e50bb75999102ee2d11c813f148fdbe7560bad9c7b44741a315d986d913", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d940f05ad92b5e9fc1d9c41efd7c0e67d7e946b2a34bec933797f190485eb457", "generation_seconds_batch": 20.805516547057778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3994154930114746, "target_z": 2.031249959522246, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.4917795658111572, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/439a1e50bb75999102ee2d11c813f148fdbe7560bad9c7b44741a315d986d913.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "43a43bf878aeca6475cfca9b85e268328a7978543cd259549c1feafd699dc9d7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d4500364f0bedffb9298b18736a2292d2b700f2ac73a60085629ba0301a49524", "generation_seconds_batch": 16.486829448025674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.270853281021118, "target_z": 3.6093750472240465, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.5005106329917908, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/43a43bf878aeca6475cfca9b85e268328a7978543cd259549c1feafd699dc9d7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "43bfa449817f4086a49ff391885e1affd0a167b1a5ec5e8ef2ff63ca4d602389", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f0e68fd6edb2be84ffe5cac644df179649cbcf42bf4967eb57317b53927a65d", "generation_seconds_batch": 16.624515205039643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1017462015151978, "target_z": 1.4921875236120232, "ce": 6.260893821716309, "genuineness": 4.770940780639648, "identity": 0.7097609639167786, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/43bfa449817f4086a49ff391885e1affd0a167b1a5ec5e8ef2ff63ca4d602389.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "75ffc375117c6b9b0a298b01566f95b5608d3df6220e981cae8019f0dfa1b8cf", "generation_seconds_batch": 16.989866191055626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4598121643066406, "target_z": 2.1406249527759535, "ce": 6.300607204437256, "genuineness": 4.570107460021973, "identity": 0.6291191577911377, "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_Astonishment_Surprise/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.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": "44738071231068c0241bd277029decd8a5ec9049c973508b55b9d63f8ac8f7f2", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "494b6c33c5ca0a99e585fac763b5e2c106cf4056d70aaf7a94f994f516235322", "generation_seconds_batch": 20.827095576096326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9162421226501465, "target_z": 1.1562500134925846, "ce": 6.24500846862793, "genuineness": 4.2249250411987305, "identity": 0.6702367067337036, "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_Astonishment_Surprise/44738071231068c0241bd277029decd8a5ec9049c973508b55b9d63f8ac8f7f2.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "0b22b92ebf3dbf522afcc36dd075705f78d535dacbf8fdd277a1c537dbf381ab", "generation_seconds_batch": 15.984411451034248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06421759724617004, "target_z": -0.3867187415671346, "ce": 6.252951145172119, "genuineness": 3.6851859092712402, "identity": 0.46276646852493286, "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_Astonishment_Surprise/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "460a5572d9829f81e7bc63fff77c1e3589bfa7233ffe1e8d78915c27cd5d72fc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5411f1c83e6f4df108fd8f69ce68c7642a460ff5047d8679db5fb3708645b221", "generation_seconds_batch": 22.10031136998441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2173663079738617, "target_z": -0.10937499325370766, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.5064013600349426, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/460a5572d9829f81e7bc63fff77c1e3589bfa7233ffe1e8d78915c27cd5d72fc.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "4694cc10d0f0dee67edf3414e9789b23e95aaa4934ff043132befc84ccec5489", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "deb93ccf2df255503b69eab5bfbf166fff88eb7bf3a0d4a12d3b509aa8a84f6e", "generation_seconds_batch": 22.952403683098964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.211315631866455, "target_z": 5.312499757133476, "ce": 5.772419452667236, "genuineness": 3.587907314300537, "identity": -0.0015476718544960022, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4694cc10d0f0dee67edf3414e9789b23e95aaa4934ff043132befc84ccec5489.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": "469ea2a4b1ec6172317958dadcfb750b6ce60f4d8cb96a89044657c8f8426387", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "354d95e3850569a346116138622d0bd9423811cac65919b0e28c6578b6f19600", "generation_seconds_batch": 16.64591131301131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1750850677490234, "target_z": 1.6250001079406775, "ce": 6.125868320465088, "genuineness": 4.174716949462891, "identity": 0.6618123054504395, "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_Astonishment_Surprise/469ea2a4b1ec6172317958dadcfb750b6ce60f4d8cb96a89044657c8f8426387.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "46a9bdbe4026e78817d16b21954695937c97f21a5b3064a8a71fd5f7fbce69e0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "67e4890051fabc84bc82f11c49c2aee5d102c74d92c032ca70aa37e2e267a9e1", "generation_seconds_batch": 15.815911814919673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8127049207687378, "target_z": 0.9687499325370765, "ce": 6.316492557525635, "genuineness": 4.143336772918701, "identity": 0.5798436999320984, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/46a9bdbe4026e78817d16b21954695937c97f21a5b3064a8a71fd5f7fbce69e0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "46e8829b4ab2f11e280509f142fc6c907ed574e857e69e13e7af8f50093b21df", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d28425bd0d73b8f9c8c49eb58fba46db5250cb8c80e2d1bd1826598342422f38", "generation_seconds_batch": 15.603134391014464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.08966326713562, "target_z": 3.2812500674629232, "ce": 5.919358730316162, "genuineness": 4.3504462242126465, "identity": 0.5343895554542542, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/46e8829b4ab2f11e280509f142fc6c907ed574e857e69e13e7af8f50093b21df.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "471d3a812cfa30522c675753a3b6f7f0838df4b01452778df2e0c0f5b48412fa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c85083dedc68a7afac71dd226710ddcf457b0ba4874df50352e9778561800e1a", "generation_seconds_batch": 21.604554562014528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7393661737442017, "target_z": 0.8359375640897773, "ce": 6.133810997009277, "genuineness": 4.030367851257324, "identity": 0.6205307245254517, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/471d3a812cfa30522c675753a3b6f7f0838df4b01452778df2e0c0f5b48412fa.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "47b9dde477642b64e588ab03e66fbd0a84ff14ca2d5561612ec79a7163d733fc", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "623ec511f7ecf3f99ca02ae4d4b91b891ed492be823be5f207ed553b59b928f6", "generation_seconds_batch": 14.693023168947548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5279777646064758, "target_z": 0.453124979761123, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.6023979187011719, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/47b9dde477642b64e588ab03e66fbd0a84ff14ca2d5561612ec79a7163d733fc.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "3bb0f0ba409ed3a900c842346b82efb5ac89c6a1719e82cf17411e118326fd54", "generation_seconds_batch": 16.43477197899483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8278040885925293, "target_z": 0.9960936808505034, "ce": 6.078212261199951, "genuineness": 4.507347106933594, "identity": 0.7065479755401611, "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_Astonishment_Surprise/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "47db2898b73266972cc3c39efaa5adbc02887521d66c7bcb9e0a92339ad0326d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9e800cb564497ef6ccde21f10bf051d6145baf261e3be4f4937c7635af687665", "generation_seconds_batch": 24.159047969034873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6444571018218994, "target_z": 0.6640625438509002, "ce": 6.252951145172119, "genuineness": 4.3504462242126465, "identity": 0.44678741693496704, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/47db2898b73266972cc3c39efaa5adbc02887521d66c7bcb9e0a92339ad0326d.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "48069b4d642da6bbd9e9d81145145c3317b57725f78957ccccfe6f771cbffab7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0a45d739f053a11074a81ef14910de2aa73c7844d84027f0d99d28796bbcae92", "generation_seconds_batch": 21.14287537103519, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8152823448181152, "target_z": 6.4062496896705525, "ce": 5.669164657592773, "genuineness": 3.672633647918701, "identity": 0.40836453437805176, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/48069b4d642da6bbd9e9d81145145c3317b57725f78957ccccfe6f771cbffab7.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "481d2cfad491966bdb29ad2fc49aea57bb410becfeae6562c7c8c27011cf8074", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dbd82698cb25863d25d510741797bb0284c0d0a826276d9fe54a976a80d9c450", "generation_seconds_batch": 16.71587846602779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06313908100128174, "target_z": -0.38867187415671345, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.6117802858352661, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/481d2cfad491966bdb29ad2fc49aea57bb410becfeae6562c7c8c27011cf8074.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "486e9ae126243030f6895f9634ca6804086d4598064ec839d77e029a5a36e218", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1494536c7c2fed456b6ff666ad3dd77e6f57f0648cad1f04b569d70d5d783f0", "generation_seconds_batch": 22.567091970006004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06745313107967377, "target_z": -0.3808593707835673, "ce": 6.046441555023193, "genuineness": 3.9676074981689453, "identity": 0.324683278799057, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/486e9ae126243030f6895f9634ca6804086d4598064ec839d77e029a5a36e218.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": "48c35c951d86e35d96a4ffca6f7677da94eb208dfcd4f6df29894d7a4a811e9b", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "339e1cf00d37ef07943f9866a4824dbdb784d5396b66abed9e4a8145c015c1a8", "generation_seconds_batch": 22.15150843805168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9032999277114868, "target_z": 1.1328124224176381, "ce": 6.173524379730225, "genuineness": 4.011539936065674, "identity": 0.3949069678783417, "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_Astonishment_Surprise/48c35c951d86e35d96a4ffca6f7677da94eb208dfcd4f6df29894d7a4a811e9b.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "48caf46eba361859fba7ca1fc1b773f3f726a04e187151601e86748f5eacc2f1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "96dbbc11d99b06301d0c6dc22874ef3cd9adcdf6bf7371fa4c4f3b7444511f35", "generation_seconds_batch": 22.567091970006004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2484238147735596, "target_z": 1.7578124763879768, "ce": 5.9431867599487305, "genuineness": 4.124508857727051, "identity": 0.6041141748428345, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/48caf46eba361859fba7ca1fc1b773f3f726a04e187151601e86748f5eacc2f1.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "48fb4f6ed9075b30b4808e37e2ca1f40bb852fb24a5d6993c147403535e9632a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "94f789a1befd553364836e95fcf2f130537824470e8dcbae9e2b2f593b2ce836", "generation_seconds_batch": 15.961635880055837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7617956399917603, "target_z": 2.687500134925847, "ce": 6.062326908111572, "genuineness": 4.319066047668457, "identity": 0.6953282952308655, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/48fb4f6ed9075b30b4808e37e2ca1f40bb852fb24a5d6993c147403535e9632a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "4909485dd9916169bcefb24108207a130c7608f48a5af89b7014978beb0d0224", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d194567ae2c6c2e99f32e27ab9215b0acdce9cc124868479b85b5f5be65b1360", "generation_seconds_batch": 22.14725066605024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12353575229644775, "target_z": -0.2792968809030058, "ce": 6.2767791748046875, "genuineness": 4.758388519287109, "identity": 0.8100289106369019, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4909485dd9916169bcefb24108207a130c7608f48a5af89b7014978beb0d0224.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "491c758a6ceb9df17721cdbbb5bd5f74fd5f8a7894e44d0fc18adc2dab9f9290", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1fef71af7426ec954c4fa5a0b0859caedd9f188e0fbf623e7bdd7ff67fbe174d", "generation_seconds_batch": 21.78619439608883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8739608526229858, "target_z": 2.8906250607166313, "ce": 6.38003396987915, "genuineness": 4.256305694580078, "identity": 0.29233720898628235, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/491c758a6ceb9df17721cdbbb5bd5f74fd5f8a7894e44d0fc18adc2dab9f9290.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "49ab61c438b74b07925ea834363f66bda498a2c9773c8f68068afa6f71f59eb6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62c7e5b1fa95f91e6bb8ea2141c58c56636b1cdb9b7a88a1a0cabf155d589aa4", "generation_seconds_batch": 22.174740009009838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2125129997730255, "target_z": -0.11816406292164328, "ce": 6.165581703186035, "genuineness": 4.607763767242432, "identity": 0.6191942095756531, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/49ab61c438b74b07925ea834363f66bda498a2c9773c8f68068afa6f71f59eb6.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "f373880fd235784e564c1488edbcc54651662785f49c7281a8fb3f8b9e7e70f2", "generation_seconds_batch": 16.0340065889759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32629603147506714, "target_z": 0.0878906427090174, "ce": 6.348263263702393, "genuineness": 4.406930446624756, "identity": 0.7012096047401428, "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_Astonishment_Surprise/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "49f946f965b42efd31668c16a76dbd9f4f77ba196388e4d267614c129538830b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d79052d2528c854c1646de7cd7ae84ee40584964a74967ad56242e3042948e70", "generation_seconds_batch": 19.72402574401349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15265558660030365, "target_z": -0.2265624898805615, "ce": 6.419747352600098, "genuineness": 4.325342178344727, "identity": 0.23656681180000305, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/49f946f965b42efd31668c16a76dbd9f4f77ba196388e4d267614c129538830b.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "4a305cd34ad3896d62ea702d1a743489091ced1809223a0e097623f9b25a0840", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "143ef3f85e8332cbd7212bb5188a3ff367e859640cac99783aa558641d21ec44", "generation_seconds_batch": 23.80222339904867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5547212362289429, "target_z": 2.312499973014831, "ce": 6.332377910614014, "genuineness": 4.369274139404297, "identity": 0.4828488528728485, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4a305cd34ad3896d62ea702d1a743489091ced1809223a0e097623f9b25a0840.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "4a7a4e6aa7b4d3aa489b732c897db802a3f87fb554769d8df875524380531989", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6bc2e1b39a7f9a441e559a25f608857fbe3d5aa62d8c41b61a46fefd5d8f80a8", "generation_seconds_batch": 23.11684836493805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06421759724617004, "target_z": -0.3867187415671346, "ce": 6.340320587158203, "genuineness": 4.758388519287109, "identity": 0.5105091333389282, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4a7a4e6aa7b4d3aa489b732c897db802a3f87fb554769d8df875524380531989.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "4af5bf885864c6e0310233594b47bf8c295458257c58a6a74fe010a877c8f6a3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "12368c775f3cc0711e56446be48a52e0fdb1556c850043f599cd067daf7cd940", "generation_seconds_batch": 17.932927962974645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9507545232772827, "target_z": 1.218750040477754, "ce": 6.268836498260498, "genuineness": 4.6956281661987305, "identity": 0.7534604072570801, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4af5bf885864c6e0310233594b47bf8c295458257c58a6a74fe010a877c8f6a3.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "4b76103de66d2f35a3ef9578eae0c66bba8ce04c4c43889e66b08eaac80d2abf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d7921f0cba6fb63496309aac9e96abf5e9854be601b1d6f4338f8e5593ce2138", "generation_seconds_batch": 20.137555740075186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12030021846294403, "target_z": -0.2851562516865731, "ce": 6.213237762451172, "genuineness": 4.2374773025512695, "identity": 0.8058096170425415, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4b76103de66d2f35a3ef9578eae0c66bba8ce04c4c43889e66b08eaac80d2abf.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": "4b994b12940bb82db7584857a84bdd989b866287b9f52d1eab94472c7e122af4", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8daa5c064ab168746f698c058938202c23c1cec52b6eafc9f8f2be844defb07d", "generation_seconds_batch": 17.403101871022955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.48569655418396, "target_z": 2.187500134925847, "ce": 6.24500846862793, "genuineness": 3.973883628845215, "identity": 0.3291075825691223, "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_Astonishment_Surprise/4b994b12940bb82db7584857a84bdd989b866287b9f52d1eab94472c7e122af4.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "4c14053b7ff6bcbe2c3b5a1ce2738f4e2c59219898b1cc7f6c3bcc319a951e7a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ad9272277138f0f3b9cedf475240ef2130bf6fee9aa782e6ef4476d95062d880", "generation_seconds_batch": 22.742209054064006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0327214002609253, "target_z": 1.3671874696416844, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.49211546778678894, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4c14053b7ff6bcbe2c3b5a1ce2738f4e2c59219898b1cc7f6c3bcc319a951e7a.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "4c377eba210abead078d7be53f3a23588dba7ab5530ffa4d1bf70c58a5c9ae89", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bc359d8625a20f969810a697dd64fc9913663837794fa3c28a3afd059162b978", "generation_seconds_batch": 20.989322626963258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6272008419036865, "target_z": 0.632812422417638, "ce": 6.141753673553467, "genuineness": 3.8922953605651855, "identity": 0.5939466953277588, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4c377eba210abead078d7be53f3a23588dba7ab5530ffa4d1bf70c58a5c9ae89.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "4c393b342bab2296583d2fe325567488c6c10ef9fd25562b626a28f738bd1aac", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ef73f152ac12709e10a9b64a628a74a317dbb82543522c12ee8748d3146d033d", "generation_seconds_batch": 29.144100747071207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4050273895263672, "target_z": 0.23046872807454988, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.4546091854572296, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4c393b342bab2296583d2fe325567488c6c10ef9fd25562b626a28f738bd1aac.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "4c7e3d3c305e8d1b348c9492bcf15b94bc4b155ec816ad6e349fa45809581b44", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5b8b75dfa66885c046860d1057a0051f0d6f4d468537ee02759aad91d7232a6e", "generation_seconds_batch": 22.504650617018342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.106919288635254, "target_z": 3.3124997571334758, "ce": 6.054384231567383, "genuineness": 4.375550270080566, "identity": 0.3682643473148346, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4c7e3d3c305e8d1b348c9492bcf15b94bc4b155ec816ad6e349fa45809581b44.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "4c81242551c2f231611b8c0652db4010b561553adbeba907d7f18c9250c38570", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d868e934494fd66f85ea2d70631ea52daa13afb90471f6f2021cefc6e2269f3c", "generation_seconds_batch": 17.316645040060394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5115808248519897, "target_z": 2.2343751011943853, "ce": 5.708878040313721, "genuineness": 3.973883628845215, "identity": 0.46111607551574707, "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_Astonishment_Surprise/4c81242551c2f231611b8c0652db4010b561553adbeba907d7f18c9250c38570.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "4c873204361ecb26a6775449c9ee4a1bf367d20a74ffae175b60d7f40a8c014f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "534aa28927e03c5023342c8f7bb2760caea67240a9dfe428ff58a72ae5a6ce5a", "generation_seconds_batch": 21.342507909052074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.07326602935791, "target_z": 5.062499649192798, "ce": 5.839932441711426, "genuineness": 3.9927117824554443, "identity": 0.10211066901683807, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4c873204361ecb26a6775449c9ee4a1bf367d20a74ffae175b60d7f40a8c014f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "4ed7bc984d34d1b5f445d6288a2a21420614735623c371956705b14d27bca3ad", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "26fa7d8188c2bf3562366fcb5b6379c7a1cf96f35b4449e5e51f3b411e10a882", "generation_seconds_batch": 22.65557683899533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.125034809112549, "target_z": 5.156250013492585, "ce": 5.998785495758057, "genuineness": 4.143336772918701, "identity": 0.5070146322250366, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4ed7bc984d34d1b5f445d6288a2a21420614735623c371956705b14d27bca3ad.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "4f4224fa2e8cfde3dbff2f2ce3d44788282abd084f0d56a27317e0d80cf1d0ac", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0511bb3d99c7c35c8946abaffe38ee69c1a1a7d232c867ee8f1a61ff9d8ceecd", "generation_seconds_batch": 20.969679609988816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15265558660030365, "target_z": -0.2265624898805615, "ce": 5.855817794799805, "genuineness": 3.9801597595214844, "identity": 0.3760901689529419, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4f4224fa2e8cfde3dbff2f2ce3d44788282abd084f0d56a27317e0d80cf1d0ac.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "4ff2037ed236832bdbd23e170cd2f026564d76bc35042b65b4a0bd4e5f2fdd01", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "eabafe06cd360717f786b9251049dddf7275ffa77eae111faa3ddf3c3b41474d", "generation_seconds_batch": 22.552628685021773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5374650955200195, "target_z": 2.2812500674629232, "ce": 6.24500846862793, "genuineness": 4.074300289154053, "identity": 0.438793420791626, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/4ff2037ed236832bdbd23e170cd2f026564d76bc35042b65b4a0bd4e5f2fdd01.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "500434d0b1ff47078958f757190b3ec0eb010aecc80b4a647012defa47d5dd10", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "09529fed7d08f82f02650c586473c59890abac16f57d42b917779a8ff50755da", "generation_seconds_batch": 16.204081194009632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.188246488571167, "target_z": -0.16210935729098258, "ce": 6.1894097328186035, "genuineness": 4.796044826507568, "identity": 0.6265196204185486, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/500434d0b1ff47078958f757190b3ec0eb010aecc80b4a647012defa47d5dd10.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "50b825f6372ca40e83254710ae60593d4e752d4c167a4e6065c6dff1b3b4ca42", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23badb11dbe136adf9feeef9c2da0305032efc94a9ac32bb28d634b49b189598", "generation_seconds_batch": 22.909438604023308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1310853362083435, "target_z": -0.26562500674629236, "ce": 6.41180419921875, "genuineness": 4.15588903427124, "identity": 0.36546820402145386, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinschauen.", "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_Astonishment_Surprise/50b825f6372ca40e83254710ae60593d4e752d4c167a4e6065c6dff1b3b4ca42.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "50c54fe2208fbbd726e1e9dc4ca6f2a0c8bdd77f4ef2b416acb040429d81180e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "65c8c601e4ca66e60f7ab78d08629f6b53e36f7e541d4678271cf65924350538", "generation_seconds_batch": 22.71211012499407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19363903999328613, "target_z": -0.15234374831342692, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.6372008323669434, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/50c54fe2208fbbd726e1e9dc4ca6f2a0c8bdd77f4ef2b416acb040429d81180e.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "50dd7f22132a340a8363743c87ab46bff97b141d06fd4fb444bca78990cbdfd0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f6547e2b5ff1f6975b463a3db09410c9ca0888a671effd6e5bfbd4bce50e1269", "generation_seconds_batch": 24.47826281597372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4373827576637268, "target_z": 0.2890624898805615, "ce": 6.109982967376709, "genuineness": 3.9550557136535645, "identity": 0.28975558280944824, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/50dd7f22132a340a8363743c87ab46bff97b141d06fd4fb444bca78990cbdfd0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "50ed928327402b10161fca6ce0b4ef3c0da73de2eb98107f8edcc0ce841386d9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a423b3d253169fd210443936de7a2cc8ac06059da07dbfc9dcef224252a49a73", "generation_seconds_batch": 16.624515205039643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907874822616577, "target_z": 2.0156251146869697, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.638042688369751, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/50ed928327402b10161fca6ce0b4ef3c0da73de2eb98107f8edcc0ce841386d9.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "518a80e38d6c3fd9a64d2a2a3c3fdfac18c04f6d5d4608b094483170bbe682fd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8999912cf207a445ad8b3202f96ab16d47eaf0646f7236b6b0edaafe0bb1d4e0", "generation_seconds_batch": 20.989739108947106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05235396325588226, "target_z": -0.4082031190969942, "ce": 6.149696350097656, "genuineness": 3.7918784618377686, "identity": 0.525456964969635, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/518a80e38d6c3fd9a64d2a2a3c3fdfac18c04f6d5d4608b094483170bbe682fd.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": "526f015843f659e53014885f779243c6b16ee134182dadbe064edea6fafe20a9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "940e0dfb7db3b1a8f801b4984595d0f7af9ab3f0ca6b1dafd04f75cf55a43142", "generation_seconds_batch": 23.6722528799437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6323741674423218, "target_z": 2.4531250877018005, "ce": 5.927301406860352, "genuineness": 4.306513786315918, "identity": 0.8022225499153137, "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_Astonishment_Surprise/526f015843f659e53014885f779243c6b16ee134182dadbe064edea6fafe20a9.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "532d958d17d01d50088d8545deba6649fee75bf840b82fac076616abc3ec3981", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29583840044601bd468af905ccc9060e726319ef2440498e4195191afaa0faf6", "generation_seconds_batch": 17.22017014597077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.831679344177246, "target_z": 4.624999676177968, "ce": 5.974957466125488, "genuineness": 4.017816066741943, "identity": 0.43496495485305786, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/532d958d17d01d50088d8545deba6649fee75bf840b82fac076616abc3ec3981.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "536d902cda620fe9dc0f0f03472aa91f363b82f95a8d15b3fba3faabb9f039e5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df459699c96eeeb3e60e718f25f9eab0155e31e4726fd6b19f3d8e9ded1d6432", "generation_seconds_batch": 21.600641182041727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3311493396759033, "target_z": 0.09667971237695303, "ce": 6.221180438995361, "genuineness": 4.061748504638672, "identity": 0.30549511313438416, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/536d902cda620fe9dc0f0f03472aa91f363b82f95a8d15b3fba3faabb9f039e5.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "54429f1e355a6bc00a64d44776227c260022a2e1b791dc36a89abc39de7579ae", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b592f95b9f177bafb85daed0a32899d57a83c54d611b8972a09ec3dd7eb63421", "generation_seconds_batch": 23.29516900505405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3562750816345215, "target_z": 1.9531250877018005, "ce": 6.205295085906982, "genuineness": 4.105680465698242, "identity": 0.695198655128479, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/54429f1e355a6bc00a64d44776227c260022a2e1b791dc36a89abc39de7579ae.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "6f9a28022f6f34d662193f8ae4aef8ce042aca45e6306f56f8719401c8a006d2", "generation_seconds_batch": 15.984411451034248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055589497089385986, "target_z": -0.4023437483134269, "ce": 6.252951145172119, "genuineness": 3.9173994064331055, "identity": 0.45311930775642395, "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_Astonishment_Surprise/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "5467a240a4f075753d987d35f3dde4c1e553279679aae91f081a44be49b5e750", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d8d3a93021e1fa54c53b75f8c4a3d4dc3ee1c8b5d9ca2c8a69aa1ab4be5e7a1d", "generation_seconds_batch": 22.243952107033692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1586880683898926, "target_z": 3.406250121433262, "ce": 5.935244083404541, "genuineness": 4.042920112609863, "identity": 0.20130963623523712, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5467a240a4f075753d987d35f3dde4c1e553279679aae91f081a44be49b5e750.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "54686de5dbd87d568fdac1f63b689ae887d1852c0ea00146a016107f82d1a2c0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b30bf4cc0922bfc27f6a3c604c3c46da6a4b77519c03feb05b492bcee648fbf0", "generation_seconds_batch": 21.419964121072553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2803404331207275, "target_z": 5.437499811103814, "ce": 6.054384231567383, "genuineness": 4.18099308013916, "identity": 0.5344885587692261, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/54686de5dbd87d568fdac1f63b689ae887d1852c0ea00146a016107f82d1a2c0.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "54783a836e60dfbaddc05cb6ac8b04b3d157e295880bb20faeb879d1d25e08e2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "244cd9327e8c30082b47f69afdd00054952369782ecfc8239285d8683afd38da", "generation_seconds_batch": 22.62885622808244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2190847396850586, "target_z": 3.5156251146869697, "ce": 5.95112943649292, "genuineness": 4.20609712600708, "identity": 0.4514814019203186, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/54783a836e60dfbaddc05cb6ac8b04b3d157e295880bb20faeb879d1d25e08e2.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "54ae1826814b78a45c1711745124151a1e5033b6450a95ed35f5ac49ab0007b8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "76c6021bc622a0a2e976269f4295aa3b999d339655ae48e33f54cee20c2b6b3f", "generation_seconds_batch": 21.283241955097765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5210678577423096, "target_z": 4.062499649192798, "ce": 5.990842819213867, "genuineness": 4.293961524963379, "identity": 0.6064680814743042, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/54ae1826814b78a45c1711745124151a1e5033b6450a95ed35f5ac49ab0007b8.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "54dde7d50bad5389397d7b76650fc1e439d12059622fa541ea0f0fd89654ad4b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "27ba17032b4f10911e188b62f7a44e35417932396808ab342060bf05710f6a35", "generation_seconds_batch": 21.419964121072553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.107778549194336, "target_z": 5.124999892059322, "ce": 6.046441555023193, "genuineness": 3.9801597595214844, "identity": 0.36830243468284607, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/54dde7d50bad5389397d7b76650fc1e439d12059622fa541ea0f0fd89654ad4b.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": "55220b6bbf36a39c245a0ff89299c7617361180f0d625d09415870e867717ea1", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bcbeeeed62556d55cbd1091cba9f31d36dc0f2add677324e979e7e25ce4fe56c", "generation_seconds_batch": 20.45118420489598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288109302520752, "target_z": 3.6406247368945985, "ce": 6.181467056274414, "genuineness": 4.268857479095459, "identity": 0.5634725093841553, "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_Astonishment_Surprise/55220b6bbf36a39c245a0ff89299c7617361180f0d625d09415870e867717ea1.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": "55bac42fae379ca0d4dd5b81801e42c505642ecea8b12773140723c719cf7b6f", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5b99c0e7306592b6822bcfda7d8a8152ec1b40679bf623a3a9fc072fc5000a6", "generation_seconds_batch": 21.733972801011987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3131345510482788, "target_z": 1.875, "ce": 6.324435234069824, "genuineness": 4.243753433227539, "identity": 0.3415603041648865, "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_Astonishment_Surprise/55bac42fae379ca0d4dd5b81801e42c505642ecea8b12773140723c719cf7b6f.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "55cb3407eccaf635770ad2f1b0f1c92cd324f23821c6bac45c82bcb2455c8c4d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "910a8b2c84d990025f760d64641610f050f7cc8acf8953cad630f913c14f5331", "generation_seconds_batch": 22.359797756071202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7005397081375122, "target_z": 0.7656250067462923, "ce": 6.125868320465088, "genuineness": 4.042920112609863, "identity": 0.33400705456733704, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/55cb3407eccaf635770ad2f1b0f1c92cd324f23821c6bac45c82bcb2455c8c4d.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "55eacf50a604984f05fb1dfdb3193357f9b385ce0a088b91c69d4ad616aa6560", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3368e26d704c813b85ae8c4b5156aca37c08827e6a2a2f62aaa5f6c3bb59fb81", "generation_seconds_batch": 23.849680697079748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9774980545043945, "target_z": 3.0781251416721394, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.4531674385070801, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/55eacf50a604984f05fb1dfdb3193357f9b385ce0a088b91c69d4ad616aa6560.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "55f3e50cd7497b3620d61f91ce9423929bd3ce785a694a44132ccb27649ccc8a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "14ca4785033764785c3ed8bb5f14c011474839876f446f0f8a39505b39d3a12c", "generation_seconds_batch": 14.086939547909424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7100269794464111, "target_z": 2.593749986507415, "ce": 6.149696350097656, "genuineness": 3.8169827461242676, "identity": 0.48865705728530884, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/55f3e50cd7497b3620d61f91ce9423929bd3ce785a694a44132ccb27649ccc8a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "561856414aea954139b3ddb7dcdc51868b58dd300d0e5625dcc86993e96ad3be", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d1e0863810292fc3ee012371a89ebda8233356ec0bee68c40c8d72a7bd3eab2f", "generation_seconds_batch": 21.259099671035074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0327214002609253, "target_z": 1.3671874696416844, "ce": 5.935244083404541, "genuineness": 4.7332844734191895, "identity": 0.6919541358947754, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/561856414aea954139b3ddb7dcdc51868b58dd300d0e5625dcc86993e96ad3be.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "5657c55e84d810ef4f0e830da2333d279c94ff1a03d86d1cae1f8eec0eed5f4e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8c712a06816b0d43ec95b86a64ab313ea88edec6d0c0083eaa855b3e37b4c23c", "generation_seconds_batch": 22.04606025700923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.115986168384552, "target_z": -0.29296875505971925, "ce": 6.117925643920898, "genuineness": 4.645420074462891, "identity": 0.6132827997207642, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5657c55e84d810ef4f0e830da2333d279c94ff1a03d86d1cae1f8eec0eed5f4e.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "575256a28eabc2f4cfa92fc8f649db4cbec330cbe67aff45989b78d880697893", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "139169b2630c01284e45ed49f19cb5666c8b9cc60fcf5db0af627a4668337d8d", "generation_seconds_batch": 17.0029988149181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4002745151519775, "target_z": 3.843749662685383, "ce": 5.824047088623047, "genuineness": 3.7793264389038086, "identity": 0.6169387102127075, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/575256a28eabc2f4cfa92fc8f649db4cbec330cbe67aff45989b78d880697893.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "5760833ba7b600a6a6ba78e9c930ce2761a77c107e95cb83e7ed78fbb52ea533", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "435e93eea027957b89761c785b9f509fd5fcc49e5dc27acc1b9e1b0d3330fb17", "generation_seconds_batch": 17.90488596400246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.5130148530006409, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5760833ba7b600a6a6ba78e9c930ce2761a77c107e95cb83e7ed78fbb52ea533.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "57aea01f0e92edef8edf0e5e4e812068c2599a252195753f13b6a9f3d41c3ef7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2af59f73f819efcfd464af14858aa6d629a3251ba74425a3bd8b3fb96cea61b7", "generation_seconds_batch": 23.11684836493805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41473400592803955, "target_z": 0.24804686741042112, "ce": 6.372091293334961, "genuineness": 4.758388519287109, "identity": 0.7089899778366089, "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_Astonishment_Surprise/57aea01f0e92edef8edf0e5e4e812068c2599a252195753f13b6a9f3d41c3ef7.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "57bbbaa2a513a2c0512731597a0ec297e6fc9a7c10256aeee4026685061a055f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9979f3dfb53e539fd96b653feb1592dc34603d01e195cb5e1699f206dc63426e", "generation_seconds_batch": 22.08045193599537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.299872487783432, "target_z": 0.04003908316052031, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.6193479299545288, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/57bbbaa2a513a2c0512731597a0ec297e6fc9a7c10256aeee4026685061a055f.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "58ae6ae8abe11303935937ed46e582b2598778403508a219340d216f749f17b9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8576b4a0c483e81daf02e442eb75179a66bed68ee6a2fc7ccf9dceff51b00e37", "generation_seconds_batch": 22.480133482953534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31901606917381287, "target_z": 0.07470703820711398, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.6199900507926941, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/58ae6ae8abe11303935937ed46e582b2598778403508a219340d216f749f17b9.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": "58b50c0f297132d4789b22d0511fb429c17ac1f7a7e1e10285c0461e233bc1f2", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Your message arrived after I had left.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7457f995460e93eaf39e1d30a181479cf364c38214306b3f49a9a1bb8e68d8a6", "generation_seconds_batch": 23.14467929804232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.937812328338623, "target_z": 1.1953124494028073, "ce": 6.316492557525635, "genuineness": 4.168440818786621, "identity": 0.32295748591423035, "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_Astonishment_Surprise/58b50c0f297132d4789b22d0511fb429c17ac1f7a7e1e10285c0461e233bc1f2.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "590d388faa9d66f64b0f17a9614f04b180993e6de23d87e2c3570d645b441992", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3714912da5d129c55e5b9fd4b8ab44504abd9acd63da462bea562703c1001468", "generation_seconds_batch": 21.83590563701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0717671811580658, "target_z": -0.3730468674104211, "ce": 6.459460258483887, "genuineness": 4.281409740447998, "identity": 0.6044285297393799, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/590d388faa9d66f64b0f17a9614f04b180993e6de23d87e2c3570d645b441992.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "5998f3a05f9de00217dabf9e31ee3f5eb5856e94ac6648c3f288b1c12e3004ed", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "820f81763619b1242bafa5ca4cc95da5dcf4e4a959f5c85fecd7da2bdde096e8", "generation_seconds_batch": 23.040852318052202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021077096462249756, "target_z": -0.4648437752985963, "ce": 5.95112943649292, "genuineness": 4.13078498840332, "identity": 0.6171932220458984, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5998f3a05f9de00217dabf9e31ee3f5eb5856e94ac6648c3f288b1c12e3004ed.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": "59bb3a84547aa1bb997b2c9d3b5b49db8df77e8bafbb3a1d41184c199b325136", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41b5870a2edb62c45a97399bece8841ba9dcf40772b6f5a48fef311fb9212c7a", "generation_seconds_batch": 17.827229888993315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9257293939590454, "target_z": 2.9843749932537076, "ce": 5.824047088623047, "genuineness": 3.9550557136535645, "identity": 0.4132879972457886, "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_Astonishment_Surprise/59bb3a84547aa1bb997b2c9d3b5b49db8df77e8bafbb3a1d41184c199b325136.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "59e2d15f40a5e57306b738ed859495eca65e28a7bbc495ec6c260d269c333d0a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "94bbd4c5ab5f4f7bf494d790210efc8094c6eccd49ee8206761ca3b46025fd8d", "generation_seconds_batch": 21.98106492497027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20388489961624146, "target_z": -0.1337890696679356, "ce": 6.395919322967529, "genuineness": 4.143336772918701, "identity": 0.4072553813457489, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/59e2d15f40a5e57306b738ed859495eca65e28a7bbc495ec6c260d269c333d0a.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "5a7e52b036cb8b109c7b1a1f181c86367e6de461e3466ccbb57415b16080b55b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0f5453b95b4bb5569e0e382c9019d501800381f1dd77fcda59e9a8c239bb5ad1", "generation_seconds_batch": 22.914798087906092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.150059938430786, "target_z": 3.3906250607166313, "ce": 5.855817794799805, "genuineness": 3.9299514293670654, "identity": 0.4331918954849243, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5a7e52b036cb8b109c7b1a1f181c86367e6de461e3466ccbb57415b16080b55b.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": "5a85189bf5f7d347393002463d6ec45661dac007420a486b1138ee4caf1bca56", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93850cf06e26a9095c995b5381d10092d14bfad97a82645703bc79b1997edb37", "generation_seconds_batch": 22.15150843805168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9938949346542358, "target_z": 1.2968749122981995, "ce": 6.022613525390625, "genuineness": 4.20609712600708, "identity": 0.5868245363235474, "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_Astonishment_Surprise/5a85189bf5f7d347393002463d6ec45661dac007420a486b1138ee4caf1bca56.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": "5a92048ffc6603bb9942dd9edb53beda585af8bbf757a676b93668df6e6888c7", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c9f5f38765e90c67612fd628f292c5e71c9e0e154ab8e1ac799928752d49e57", "generation_seconds_batch": 16.716558458982036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2967374324798584, "target_z": 3.65624979761123, "ce": 6.173524379730225, "genuineness": 4.2249250411987305, "identity": 0.6241089105606079, "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_Astonishment_Surprise/5a92048ffc6603bb9942dd9edb53beda585af8bbf757a676b93668df6e6888c7.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "5b9cd61dda7acab0603012c4f0d1b49a1d9346b3dcce47c32eab1c65b39eb8a6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3710b2301cbf86576c21f5a4462f03e93a6d78b05794b33f78dea38a0c4e4153", "generation_seconds_batch": 16.96989339601714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0004931390285491943, "target_z": -0.5039062651791578, "ce": 6.41180419921875, "genuineness": 4.18099308013916, "identity": 0.5382972955703735, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5b9cd61dda7acab0603012c4f0d1b49a1d9346b3dcce47c32eab1c65b39eb8a6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "5cd3292919347ad0bae4fdbdeef0a70bdbdddce13f6cff7e42404149db8a71a8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b3c20e370090c0575ca99c5ed260f8cbb3b4dd3b6cc04ba7b2b03d115e165d2f", "generation_seconds_batch": 21.858603856991976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6582584381103516, "target_z": 2.500000053970339, "ce": 5.792276382446289, "genuineness": 4.049196243286133, "identity": 0.6015133261680603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5cd3292919347ad0bae4fdbdeef0a70bdbdddce13f6cff7e42404149db8a71a8.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "5cdb1bf0a24b9540263fcd0a2284cb997bbce572eded4bed11796623ae9422fc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "846de9c89e67df30baba1e227282c0e02e8019ecd3850a042eaebba46fc8861d", "generation_seconds_batch": 22.50033313105814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4654240608215332, "target_z": 0.3398437213282575, "ce": 6.205295085906982, "genuineness": 4.030367851257324, "identity": 0.30889132618904114, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5cdb1bf0a24b9540263fcd0a2284cb997bbce572eded4bed11796623ae9422fc.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "5d030582156bb3ddafff3f456125d800e2247a9426b85fc3afc93ef43e3f2cfc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "08f81ee1531ec7edefcf8f017d8ebb09cdbf4fe7aece6b9e4a284c10c9863a1e", "generation_seconds_batch": 19.618143899017014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1328036785125732, "target_z": 3.3593749392833687, "ce": 5.752562999725342, "genuineness": 4.218649387359619, "identity": 0.7003782987594604, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5d030582156bb3ddafff3f456125d800e2247a9426b85fc3afc93ef43e3f2cfc.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": "5d82a8fcb2e4eb2080ee6080551873978f326e39698a71042852aa09133e198a", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c26d883a0009a2476a9a976fcc7971a75501f5c038f41ea475597a26c37fb68f", "generation_seconds_batch": 23.29614661098458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8144233226776123, "target_z": 4.593749986507415, "ce": 6.252951145172119, "genuineness": 4.118232727050781, "identity": 0.45235955715179443, "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_Astonishment_Surprise/5d82a8fcb2e4eb2080ee6080551873978f326e39698a71042852aa09133e198a.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "5d8fbdfe549b39b2a82ae029ddf0ac90246998c320c1a6b18514bd9a85ceb0a7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1bb789a2998778e853d20144a62c260c4fae0110303e8920c44d907ac0994643", "generation_seconds_batch": 20.462730696075596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35649436712265015, "target_z": 0.14257813933587124, "ce": 6.046441555023193, "genuineness": 4.15588903427124, "identity": 0.46930909156799316, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5d8fbdfe549b39b2a82ae029ddf0ac90246998c320c1a6b18514bd9a85ceb0a7.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": "5d9641e69b993049173fef5f43dbb0c2d20e3368b517f6255717b269ee72d9a9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75ce3844040686e140f9f5cdbc975e074d95bd382114833683b90ee680bfd2a4", "generation_seconds_batch": 23.14697915792931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.624605178833008, "target_z": 4.249999946029662, "ce": 5.935244083404541, "genuineness": 4.2249250411987305, "identity": 0.7635871767997742, "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_Astonishment_Surprise/5d9641e69b993049173fef5f43dbb0c2d20e3368b517f6255717b269ee72d9a9.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "5da413d426900891bc40fa634b8cfa2a30a16a09ec34857b37f606302d2c3858", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "22ef503de8f9cbedfe34e919fa1a6bfae96b7069bf437f6cb68c71816f5c7607", "generation_seconds_batch": 22.54559558897745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0206384658813477, "target_z": 3.156250013492585, "ce": 6.268836498260498, "genuineness": 3.9173994064331055, "identity": 0.4946281313896179, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5da413d426900891bc40fa634b8cfa2a30a16a09ec34857b37f606302d2c3858.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "30d3be8da02ad314fd88a26ebae5c9b36f13c92f788d47a2d2f1a4f80200036b", "generation_seconds_batch": 17.790758160990663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008134961128234863, "target_z": -0.4882812584328654, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.7223475575447083, "hypothesis": "La route tourna 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": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "5e5b0780df28ad74efb64397768678bb4f7c186af211fc40f0189b55d0f9d997", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3c3c893f57f58a0dd8f5aa4959f1a1750b90cf58f8307e9ee65d4e8b713544c8", "generation_seconds_batch": 22.68692596803885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2869303226470947, "target_z": 0.01660154605591241, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.45460960268974304, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/5e5b0780df28ad74efb64397768678bb4f7c186af211fc40f0189b55d0f9d997.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": "5e898f4026b323c412a429ae84057c45e03864309f9b1a5a8c2db352c58f2816", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1454dae2de78dd7f5aecbd8313dad711ea9de0ae30aa847e849dfd536e1e38d6", "generation_seconds_batch": 16.07354987389408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9343575239181519, "target_z": 3.000000053970339, "ce": 6.197352409362793, "genuineness": 4.250029563903809, "identity": 0.6280311346054077, "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_Astonishment_Surprise/5e898f4026b323c412a429ae84057c45e03864309f9b1a5a8c2db352c58f2816.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": "601bb2b2728cdd555b393675e707401d6f7ca51b65024e0727acb75476040bb9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fac62f0e30a1f78c6feb308b89d3a869010e0d611756859934111e13c656a89", "generation_seconds_batch": 14.272608319995925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3217626810073853, "target_z": 1.890625060716631, "ce": 6.221180438995361, "genuineness": 3.6789097785949707, "identity": 0.41080182790756226, "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_Astonishment_Surprise/601bb2b2728cdd555b393675e707401d6f7ca51b65024e0727acb75476040bb9.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "607f2792c90025496def1462db778d6cd836cbb57fa66fec780283d0d34e8a96", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "15864fdfae97075997e1d921c76d8e582e48633677e94e2d7d60491b36f872b5", "generation_seconds_batch": 23.249038784997538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7531675100326538, "target_z": 2.6718750742092157, "ce": 5.454712867736816, "genuineness": 3.8922953605651855, "identity": 0.3486272096633911, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/607f2792c90025496def1462db778d6cd836cbb57fa66fec780283d0d34e8a96.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": "60c8de7e76daf30d24e15a68a0fbc797ce0be6389f91c9c418f308ddc3b8563e", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "be88ebbde6ebd982010e5f0eefb11c578e4682126ca74feb7381283348730e35", "generation_seconds_batch": 17.391301196999848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 6.141753673553467, "genuineness": 4.105680465698242, "identity": 0.3414015471935272, "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": 0.120000000000001, "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_Astonishment_Surprise/60c8de7e76daf30d24e15a68a0fbc797ce0be6389f91c9c418f308ddc3b8563e.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "614561460887ad8467d996ca52a5cad6d8018fa624fd539293d69c4c3be8c3c2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "60f258000420cadeb7c412f231803a0d0be36b8fe018bbda44d2c7e44eafa5bf", "generation_seconds_batch": 21.36243586288765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9516136646270752, "target_z": 3.031249959522246, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.5446890592575073, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/614561460887ad8467d996ca52a5cad6d8018fa624fd539293d69c4c3be8c3c2.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "6214438d0fe083357e1e3e8918110a2c27687bcc524b32cdf5ba1b23029efb1f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "198f22ac44731a43ddb837f2d3180672b2f4a2b07119e909c328e2303945abe1", "generation_seconds_batch": 21.589569165953435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08470931649208069, "target_z": -0.34960938427615196, "ce": 5.990842819213867, "genuineness": 4.6705241203308105, "identity": 0.8128131628036499, "hypothesis": "J'ai trouvé la maison une 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_Astonishment_Surprise/6214438d0fe083357e1e3e8918110a2c27687bcc524b32cdf5ba1b23029efb1f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "6237da86d96485a50b8f3c0e737429b3a148fa513b25e797778fdf879a6ef987", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4bcbc2ad17d043cb65ed2c2d1d4713bce5e4d3e57637d6c34bccd58a5133fac7", "generation_seconds_batch": 20.207054694066755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.07326602935791, "target_z": 5.062499649192798, "ce": 5.967014789581299, "genuineness": 3.973883628845215, "identity": 0.519134521484375, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6237da86d96485a50b8f3c0e737429b3a148fa513b25e797778fdf879a6ef987.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": "625d6c4140402cbbb5c5613736df1ea73ae3be806192304f3378f27bcb522cdf", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1710dbb7af9cec78f5d30b6a9d522b0f30b0cb0f512f195b30c191720d6772a", "generation_seconds_batch": 23.085536765982397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7790517807006836, "target_z": 2.718750040477754, "ce": 6.205295085906982, "genuineness": 4.3127899169921875, "identity": 0.5871585607528687, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter. Bis zu dem kleinen Holztor. Ich ich warte auf der anderen Seite.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/625d6c4140402cbbb5c5613736df1ea73ae3be806192304f3378f27bcb522cdf.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "629aa048bac94adb57ecb8b69184e13341516b0a64815fa55b8c3e241ef52d96", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "310372f98c787d8959b4c8ba3ab35b74d19c7db31a4e4918947bbed2234ff5f8", "generation_seconds_batch": 21.342507909052074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.125034809112549, "target_z": 5.156250013492585, "ce": 5.788304805755615, "genuineness": 3.6851859092712402, "identity": 0.03591437265276909, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/629aa048bac94adb57ecb8b69184e13341516b0a64815fa55b8c3e241ef52d96.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "62b22da08bc694e4326a6618b1caa10aed17c485675768f11c90873b34b4a7fc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "71ddc9ccf0c2fa0535a3d6a4115a61eb8ff72d666bd9d3e27c81a7de21760dc0", "generation_seconds_batch": 19.41514660802204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8135641813278198, "target_z": 2.7812500674629232, "ce": 5.9431867599487305, "genuineness": 3.9425034523010254, "identity": 0.3345787227153778, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/62b22da08bc694e4326a6618b1caa10aed17c485675768f11c90873b34b4a7fc.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "63d65ea6dfcf71ff43d3fb61e96fa157d5cb2caa0bb4dc18d50f53fccff1caaf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "43358ac3e2af0b8749d30014d9200d83c976548b2e4fc9cf48806370f29653e6", "generation_seconds_batch": 16.99005096592009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4341472387313843, "target_z": 0.28320314608216357, "ce": 6.284721851348877, "genuineness": 4.319066047668457, "identity": 0.5284517407417297, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/63d65ea6dfcf71ff43d3fb61e96fa157d5cb2caa0bb4dc18d50f53fccff1caaf.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "6467940d86d657d935409093223f07d6439c0f3831bea9a8dbf397747682481a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6bddab8068dc0854f5a6ccad48d3623cd4e136467fc612bf54e27681919584d1", "generation_seconds_batch": 22.690680117928423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8644735813140869, "target_z": 1.062500080955508, "ce": 6.229123115539551, "genuineness": 4.18099308013916, "identity": 0.730556070804596, "hypothesis": "De deur staat nog open. ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6467940d86d657d935409093223f07d6439c0f3831bea9a8dbf397747682481a.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "6541ed0a5a53841daa156dddce26999528354a0be697ad60a3ff34b8f1c174b2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "505b361945da47efc66a562d87dac16d54693ae2c6a5a19940ca62881c23b81e", "generation_seconds_batch": 16.446935564978048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.486555576324463, "target_z": 3.999999838088984, "ce": 6.1020402908325195, "genuineness": 4.017816066741943, "identity": 0.5012655258178711, "hypothesis": "The 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_Astonishment_Surprise/6541ed0a5a53841daa156dddce26999528354a0be697ad60a3ff34b8f1c174b2.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "6579ec705c14c1e0210eb8a38488d46f4d3ad83e31d1d571416b251de0fd9375", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "79c68e9e83d085c170ce3fe338454ba832e689efd4271918961b8864961d1daf", "generation_seconds_batch": 23.073460677987896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.590951919555664, "target_z": 5.999999838088984, "ce": 5.597680568695068, "genuineness": 3.747946262359619, "identity": -0.03614739328622818, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6579ec705c14c1e0210eb8a38488d46f4d3ad83e31d1d571416b251de0fd9375.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "65922fa509ffad755dc54810467cee6d84c0c06616abcd36c339e3ac391685e6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "caf7651fe2efc0738acfc6b7c657b10793111c094c44317f26f0c083aa76de0c", "generation_seconds_batch": 16.280514121055603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07500271499156952, "target_z": -0.36718749662685385, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.5535712242126465, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/65922fa509ffad755dc54810467cee6d84c0c06616abcd36c339e3ac391685e6.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "66185f7188f40ee79fd44539f488e4ea5b33862d14053f0dd3741a4143691d23", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fefdb5fd3608183f8c41778f2ae06efd5e99fcc1196f0a0a1befd5a43d8f03ff", "generation_seconds_batch": 23.233206520904787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0715478658676147, "target_z": 1.4375000269851694, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.7242807149887085, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/66185f7188f40ee79fd44539f488e4ea5b33862d14053f0dd3741a4143691d23.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "669b2d9a61e94e209a327b1ffe4ffe1ae081c0188928ac5a53425337a67a0e06", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ad0a47f792281594380b7632807475394658d722ebe5c714d724f39b7be242e8", "generation_seconds_batch": 16.344008821994066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07392419874668121, "target_z": -0.3691406292164327, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.6801580190658569, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/669b2d9a61e94e209a327b1ffe4ffe1ae081c0188928ac5a53425337a67a0e06.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "66c3c2a39cf97277359a1763053b34496f9bdeb76cdf780b8105d2fcff878a6c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "720530a3898e03608ae7b75eeb6b5dc2077b05fbd6e6238039bb8bf6f319300a", "generation_seconds_batch": 21.19205417507328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04480437934398651, "target_z": -0.42187499325370764, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6841033697128296, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/66c3c2a39cf97277359a1763053b34496f9bdeb76cdf780b8105d2fcff878a6c.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "66f65f5a9fca5dc38c29244bbb2d9a4a54be0c5a07df9d1d5c3a429cd0574fb5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f21830c651e6d208b4984403976037af4e37717cbeb334d852714c3fa5a3601d", "generation_seconds_batch": 20.12719302298501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 5.895530700683594, "genuineness": 3.7291181087493896, "identity": 0.531017541885376, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/66f65f5a9fca5dc38c29244bbb2d9a4a54be0c5a07df9d1d5c3a429cd0574fb5.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "675069a821b450ef57e8d7989c828748eb596629985f86a3fe992d38dc47a63b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7c01cbd94e5607aebb80f56acf10197e3bbec31954a3f2a1ae2fc514f3bff2f6", "generation_seconds_batch": 14.521804051008075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8912169933319092, "target_z": 2.9218749662685384, "ce": 6.054384231567383, "genuineness": 4.20609712600708, "identity": 0.25389066338539124, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/675069a821b450ef57e8d7989c828748eb596629985f86a3fe992d38dc47a63b.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "67fa6aaf150ffc8db250bd2b9db2d4604f2d95ec0cfd9736796e0e0af3889368", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "befb4cf4710add87cae9b9b4261a8cb1b99e58c33100306aec841caf7e28e18f", "generation_seconds_batch": 20.675911417929456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06098206341266632, "target_z": -0.39257811235070184, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.7564742565155029, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/67fa6aaf150ffc8db250bd2b9db2d4604f2d95ec0cfd9736796e0e0af3889368.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "688af0d35cc85fbc2b3b161db1d9089ee04896d0dc9379bda9335025581abae4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3388e1da94b819a96015718b8c5ed3c96d97f13e43eb50c5573bab44e6f86b8e", "generation_seconds_batch": 20.675911417929456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18501093983650208, "target_z": -0.16796875505971925, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.7147958874702454, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/688af0d35cc85fbc2b3b161db1d9089ee04896d0dc9379bda9335025581abae4.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "68ea562f20cf0bf0675e6729d6d1a4133eb276a584c11c60ea53a18e6c666b32", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f345f03d14b378b563b9d01c1873ffb3b4e61f91829930e85a9f0659919c47bc", "generation_seconds_batch": 22.913248167955317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1966552734375, "target_z": 1.6640625438509002, "ce": 6.427689552307129, "genuineness": 4.570107460021973, "identity": 0.42937904596328735, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/68ea562f20cf0bf0675e6729d6d1a4133eb276a584c11c60ea53a18e6c666b32.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "69225f84c340142645efa5568429a4d7dd358a525bdeaa83330b09bbc32239e8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "30c43fd1bf78c4ee5b6b034af81371f6e5dbe3973ee5187189ea8bc3f6c08afb", "generation_seconds_batch": 22.062110222992487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348505973815918, "target_z": 3.749999730148306, "ce": 5.967014789581299, "genuineness": 3.578493118286133, "identity": 0.3475000858306885, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/69225f84c340142645efa5568429a4d7dd358a525bdeaa83330b09bbc32239e8.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "697ec36b5a7107a7b2626d47ded4b5b806cf9ee852e81f325db612a86c06976a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "14bb7c90626e2918d59017538137c24043d8a6be1b60207da86cdabea6743fff", "generation_seconds_batch": 21.53679089504294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6591174602508545, "target_z": 4.312499757133476, "ce": 6.181467056274414, "genuineness": 4.174716949462891, "identity": 0.3690683841705322, "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_Astonishment_Surprise/697ec36b5a7107a7b2626d47ded4b5b806cf9ee852e81f325db612a86c06976a.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "baa8ce1a315d3b58a0d8acbb944ed57e98983ef526f629bd4f5d731ba34e3e99", "generation_seconds_batch": 16.82053467503283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3106575906276703, "target_z": 0.05957030111563167, "ce": 6.324435234069824, "genuineness": 3.7793264389038086, "identity": 0.4012482762336731, "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_Astonishment_Surprise/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "6a6c865391f21a48b128b4b19376486d535c4b3c5984f1976176142ab6d799fe", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "536363263eab5559a21ea63869833d75265d07eace12700d8be496361945eaf9", "generation_seconds_batch": 22.71211012499407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1451060026884079, "target_z": -0.24023436403727494, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.699683427810669, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6a6c865391f21a48b128b4b19376486d535c4b3c5984f1976176142ab6d799fe.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "6af899af46257d5f13482c4cfcf7c1c25b45781146c8d47d70ad496273fc0083", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e5dd02c68bd8cfcb2fac480f8175d39974e5fb7d9ff6e95eb57025ad342ea6f5", "generation_seconds_batch": 16.382089612074196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1414318084716797, "target_z": 3.375, "ce": 6.070269584655762, "genuineness": 4.2249250411987305, "identity": 0.5138310194015503, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6af899af46257d5f13482c4cfcf7c1c25b45781146c8d47d70ad496273fc0083.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "6b053b139b25c3218e39d5c2113660265385e671319726e9a8e6d216508963e6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3de35c2e0f787be2f25f38af14f93d31fadccd6502c998068ede791422b0f719", "generation_seconds_batch": 21.95394108898472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5383241176605225, "target_z": 4.093749770626061, "ce": 6.070269584655762, "genuineness": 3.9299514293670654, "identity": 0.7149759531021118, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6b053b139b25c3218e39d5c2113660265385e671319726e9a8e6d216508963e6.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "a5111ad92f4c8c8f9f977c60ce8fd9a3dc18ab0117baf955713558fb29daccc0", "generation_seconds_batch": 16.989866191055626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40556666254997253, "target_z": 0.2314453213545087, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.7063271403312683, "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_Astonishment_Surprise/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "6c31e532a6c75309b9e7921409dfed0c0a1dd0a040e1af052775b33c948f1614", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6cc9fd59d95f5626b92193e34bcca466e6423989d4729fd0277526f546a92d59", "generation_seconds_batch": 17.742100927978754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3195553123950958, "target_z": 0.07568357751673405, "ce": 6.0146708488464355, "genuineness": 4.331617832183838, "identity": 0.4822383522987366, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6c31e532a6c75309b9e7921409dfed0c0a1dd0a040e1af052775b33c948f1614.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "6d5aa574fde703457163fad1dff5f7345031dafe22b0acdd80f6baecba4058ea", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae61a46d16f0695d38dcfadcc0e59c16ecf09c02d5aa901034933c9b3edf9093", "generation_seconds_batch": 21.702934039058164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8903578519821167, "target_z": 1.1093750472240465, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.5600090026855469, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6d5aa574fde703457163fad1dff5f7345031dafe22b0acdd80f6baecba4058ea.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "6d9d3f78fc322164a6a464cc770d8aefc011d6190c166c23d01c8af1c9e3c28f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ca796abcf4e8e9292e457d4e2794190e8d5fa91660edfed04f03cdda463e151", "generation_seconds_batch": 22.352931184927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30661317706108093, "target_z": 0.05224609438246491, "ce": 6.125868320465088, "genuineness": 4.720732688903809, "identity": 0.7102371454238892, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6d9d3f78fc322164a6a464cc770d8aefc011d6190c166c23d01c8af1c9e3c28f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "6e02054d49a4001ee0a87efed33db8409fc3c0d0f4065cf75f30eec5bd3558d6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0f707d490e0c62a1f117d07606372f687be64b178d90799c9bdc2fa08d2d46ea", "generation_seconds_batch": 25.79019616707228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8739608526229858, "target_z": 2.8906250607166313, "ce": 6.078212261199951, "genuineness": 4.049196243286133, "identity": 0.17149198055267334, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6e02054d49a4001ee0a87efed33db8409fc3c0d0f4065cf75f30eec5bd3558d6.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "6e25d89e78128dcb7676e589afa5f3e6247cff49841254bccd01c4cfce138472", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "319d1951b6ca957e37e6403b18ffe5b7b59cadcf5238e3718e584eb30b7533b8", "generation_seconds_batch": 19.167389909969643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7445393800735474, "target_z": 2.656250013492585, "ce": 6.078212261199951, "genuineness": 4.024092197418213, "identity": 0.3830917477607727, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6e25d89e78128dcb7676e589afa5f3e6247cff49841254bccd01c4cfce138472.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "6e48af979522c25f41cdfb096b7c99c5da3c7d0e45d785328b9e893bf2c560f1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "406bf42398aade6aeb81b3888ebef92d7d8d4f7a2e7d737a7d8092818dea0589", "generation_seconds_batch": 20.086374146980233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2354817390441895, "target_z": 1.734375101194385, "ce": 6.268836498260498, "genuineness": 3.9801597595214844, "identity": 0.4578549861907959, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6e48af979522c25f41cdfb096b7c99c5da3c7d0e45d785328b9e893bf2c560f1.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "6ec4525028a9c760621b083514b1f0ac6b6dee45b5de808741fd3cdec6133747", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9c5fe51608eab0bce748fc3aa18ffeb804770e7c6ab01b794e8d7001675b920f", "generation_seconds_batch": 21.510598473949358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.468440294265747, "target_z": 2.156250013492585, "ce": 6.038498878479004, "genuineness": 3.973883628845215, "identity": 0.37941592931747437, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6ec4525028a9c760621b083514b1f0ac6b6dee45b5de808741fd3cdec6133747.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": "6f0c2e77d7c9319236c2f2f36f560087166aa2a8992b053f0b1e3527e7d1b410", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "731182033b40e0c03e3fe3455e6be357a64b1c8d2714fcfa7cf93699ae98b82d", "generation_seconds_batch": 20.28510586800985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.756622314453125, "target_z": 0.8671874696416845, "ce": 5.998785495758057, "genuineness": 4.036643981933594, "identity": 0.5901256799697876, "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_Astonishment_Surprise/6f0c2e77d7c9319236c2f2f36f560087166aa2a8992b053f0b1e3527e7d1b410.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "6f4e67cea81e458067d46ddbef27629426dd0b3c201f5d409f73374c73690641", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8300d001a0881865cbbf3fe9671441eebd7c006db38d6df8525dd9eef7900b51", "generation_seconds_batch": 21.62604217894841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8394484519958496, "target_z": 2.8281250337314616, "ce": 5.959072113037109, "genuineness": 4.306513786315918, "identity": 0.45478585362434387, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6f4e67cea81e458067d46ddbef27629426dd0b3c201f5d409f73374c73690641.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": "6f84b2869b35a6386dba9cb71e97302fb4ffa470d3f31b212ea0fa6f4c46f08a", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87bbce9ce1b7c63bb849f15fae38bdca6d2e30f1a1ac6ee51bacf621eb0e5c60", "generation_seconds_batch": 20.28510586800985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5150356292724609, "target_z": 0.42968749662685385, "ce": 6.221180438995361, "genuineness": 4.118232727050781, "identity": 0.7543443441390991, "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_Astonishment_Surprise/6f84b2869b35a6386dba9cb71e97302fb4ffa470d3f31b212ea0fa6f4c46f08a.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "6f92fbfe00db89d8b90642114e584f2ab1e617f26e1a84e4b19994eb86c2044e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "879f3e8132e8dfe366eb50152a3155de442d25560070eab71cc214518727c540", "generation_seconds_batch": 21.01079299999401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16344070434570312, "target_z": -0.20703124494028075, "ce": 6.141753673553467, "genuineness": 4.005263805389404, "identity": 0.7063404321670532, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6f92fbfe00db89d8b90642114e584f2ab1e617f26e1a84e4b19994eb86c2044e.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "6f9c5bfc0ee3840abaddb221861f8d2c69c71efce77426f1533d109972e31629", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "07b451de77dcc44cb1c116394b716106244c8da7f61f390b4b30fe8f378974fe", "generation_seconds_batch": 24.363525978988037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0810351371765137, "target_z": 3.2656250067462924, "ce": 6.046441555023193, "genuineness": 4.13078498840332, "identity": 0.5496189594268799, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6f9c5bfc0ee3840abaddb221861f8d2c69c71efce77426f1533d109972e31629.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "6fcad1e1cf4cd933bfd93b2d02534b0e9456aea2b5061c33cebaefcefb0295cf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d989242b6d56bc532e46dc36520ff5b9fbb792eb726a1b69cec3ffc6180ce09c", "generation_seconds_batch": 16.10782462602947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4347870349884033, "target_z": 3.906249905551907, "ce": 6.09409761428833, "genuineness": 4.15588903427124, "identity": 0.4809921383857727, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6fcad1e1cf4cd933bfd93b2d02534b0e9456aea2b5061c33cebaefcefb0295cf.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "6fd7b1912359fc8d64c0813eef465279f30924973c2ca9232b8f701244806640", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82eed2b2cb41ef46ec65792e753ca2d55390470533911d6f39718d11852a9bb7", "generation_seconds_batch": 24.39473810105119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8731015920639038, "target_z": 1.0781249257907841, "ce": 6.117925643920898, "genuineness": 3.9801597595214844, "identity": 0.40246203541755676, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/6fd7b1912359fc8d64c0813eef465279f30924973c2ca9232b8f701244806640.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": "701959bb1ca4f0373d61e12cb346800e5dc7b41973813ef64f2b1d73d3de4029", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Your message arrived after I had left.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd2cf19a2bf215961461fc1ab19b9a2625385b424b5748be691e671ee129f630", "generation_seconds_batch": 14.430117215961218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907874822616577, "target_z": 2.0156251146869697, "ce": 6.09409761428833, "genuineness": 4.030367851257324, "identity": 0.3652282953262329, "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_Astonishment_Surprise/701959bb1ca4f0373d61e12cb346800e5dc7b41973813ef64f2b1d73d3de4029.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "704db2415875cf0b295f68ba22cedcc40393d614b84528b774965ecd9fa382f8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ba7e7f7e48eabd8d6aedd40a638088f3b15ca931f1ee322c91925e45ae894813", "generation_seconds_batch": 23.598710079095326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.287250280380249, "target_z": 1.8281250337314616, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.5196340084075928, "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_Astonishment_Surprise/704db2415875cf0b295f68ba22cedcc40393d614b84528b774965ecd9fa382f8.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "7065dac10d59864cd7a0c362f07530615297df0e0485458fbdadeea17030c4ba", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "54cbdbf9c60bce8be1663f201a9273a34c5ca9067ffcdb915ff6453aea51c549", "generation_seconds_batch": 21.67378861794714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1414318084716797, "target_z": 3.375, "ce": 6.006728172302246, "genuineness": 4.243753433227539, "identity": 0.5216326117515564, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7065dac10d59864cd7a0c362f07530615297df0e0485458fbdadeea17030c4ba.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "7086c933b9d2e07cc440824e1147b4ca96f5769047103e063eb0a0557aa7eb55", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f186dfe7a9edfcf61cb382b8fcd491ed0fbd487564398f84ebd6175c445695cb", "generation_seconds_batch": 16.344008821994066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13647790253162384, "target_z": -0.2558593707835673, "ce": 6.2767791748046875, "genuineness": 4.595211505889893, "identity": 0.45326265692710876, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7086c933b9d2e07cc440824e1147b4ca96f5769047103e063eb0a0557aa7eb55.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "710242471a5a3b72c026b5feb6d90971c093ae17e77668ee759e4a9da1cac332", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ed067290bf715288920414fa0014b7716e371039e4be615286a0c1798712c018", "generation_seconds_batch": 17.932927962974645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06421759724617004, "target_z": -0.3867187415671346, "ce": 5.982900142669678, "genuineness": 4.3881025314331055, "identity": 0.6225177645683289, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/710242471a5a3b72c026b5feb6d90971c093ae17e77668ee759e4a9da1cac332.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "712a95f55b169f5d2bc0c9d50404653486f0ea9fa8bc166997a4afbe399292d0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "031c9b3ef01d8f5add8a58928a1ddc571113d8548c4790608738f61299aeae6b", "generation_seconds_batch": 23.220049284980632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9248702526092529, "target_z": 1.1718750742092159, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.7249357104301453, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/712a95f55b169f5d2bc0c9d50404653486f0ea9fa8bc166997a4afbe399292d0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "7135dea5fafe4c83c3657044323aee42539a37e3832d41e583ab0380d22c9a27", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "af7bb4120874ec781840413e6ef312b14e07121403312bfe9be87761efca2bed", "generation_seconds_batch": 16.204081194009632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18285392224788666, "target_z": -0.17187499325370764, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.6945728063583374, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7135dea5fafe4c83c3657044323aee42539a37e3832d41e583ab0380d22c9a27.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "718cf8dc38504abf9c25427aa62e658a41aaab7f6f4c96dd3ffd8e208e1810b8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bcfcc5857017cfdd8b72ca532a2a0acd9ba9057eb95e0255fb06c80397e8b6a6", "generation_seconds_batch": 20.63669736403972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.149200677871704, "target_z": 1.5781249257907841, "ce": 6.1020402908325195, "genuineness": 4.337893962860107, "identity": 0.6111531257629395, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/718cf8dc38504abf9c25427aa62e658a41aaab7f6f4c96dd3ffd8e208e1810b8.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "71f09ae1cbca66913a4cf63cfa7013e9c0d8210b0c0e61ed1c4528e9fc5421f4", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f715c6719ca4e886c24ede4d6d0473f1ab68d6a3e5a3d419f280024cf80fa55f", "generation_seconds_batch": 15.564999714959413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18662871420383453, "target_z": -0.16503905617535092, "ce": 6.324435234069824, "genuineness": 4.808597087860107, "identity": 0.612364649772644, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/71f09ae1cbca66913a4cf63cfa7013e9c0d8210b0c0e61ed1c4528e9fc5421f4.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": "735423d256c3389353a3d7a9aec8ca7637fe550a3b705777d4ae824f9e75e298", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d51c5bcc0324ad11a0c267259bba5b03a6e8f7580a891495661804b5603680ba", "generation_seconds_batch": 23.39177747699432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2786221504211426, "target_z": 1.8124999730148306, "ce": 6.340320587158203, "genuineness": 4.011539936065674, "identity": 0.5693451166152954, "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_Astonishment_Surprise/735423d256c3389353a3d7a9aec8ca7637fe550a3b705777d4ae824f9e75e298.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "737f710da18b042d858b8230716a03b69a848f469e25a9176db66164dceccbc4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d6d529e42867096559237a0e6f4e60f803e49bebe8d4dbb255979c09f6aa48f5", "generation_seconds_batch": 22.73095892299898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7911347150802612, "target_z": 0.9296874966268538, "ce": 6.23706579208374, "genuineness": 4.337893962860107, "identity": 0.40790510177612305, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/737f710da18b042d858b8230716a03b69a848f469e25a9176db66164dceccbc4.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "73ac1b6692fc48323e7ae890397ff1ac430e94ebe6051c58189ce35e0f8e2a81", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "731e5e3c160f4095276188a9122e4e03310e267bff2ac88a75d2b17c7920a202", "generation_seconds_batch": 17.695559209096245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1414318084716797, "target_z": 3.375, "ce": 6.229123115539551, "genuineness": 4.3881025314331055, "identity": 0.3429889976978302, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/73ac1b6692fc48323e7ae890397ff1ac430e94ebe6051c58189ce35e0f8e2a81.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "73dd6d7820514553160afea715486211ff420eda45807d7809e41c73fec5f0bb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7525699291f187d4ea43c09ce02587be4523a95f717bd6061f311191c33ca275", "generation_seconds_batch": 14.590224985033274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.866191864013672, "target_z": 4.687499919044492, "ce": 6.038498878479004, "genuineness": 3.9425034523010254, "identity": 0.1551850140094757, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/73dd6d7820514553160afea715486211ff420eda45807d7809e41c73fec5f0bb.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "73f46081ca4ad742f5c6bf94de706f95c47bb7dcdfb2b6bb33138456a7ba041d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2c257b7bb6f63e38c2ca0fdfe63532156d863bcd0c9eca400eea54571e33e66a", "generation_seconds_batch": 23.43496055295691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3994154930114746, "target_z": 2.031249959522246, "ce": 6.340320587158203, "genuineness": 4.344170093536377, "identity": 0.4424664080142975, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/73f46081ca4ad742f5c6bf94de706f95c47bb7dcdfb2b6bb33138456a7ba041d.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": "7432aac556065cc790d0527dc3852c1e63533e724aa33cfd65d9a6c62678d51b", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2255a44a296e4ef77130e7b846da4544017d50601c4841413f90fb25afcd45b7", "generation_seconds_batch": 16.231904129963368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1768033504486084, "target_z": 5.249999946029662, "ce": 6.292664527893066, "genuineness": 3.9550557136535645, "identity": 0.4902874529361725, "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_Astonishment_Surprise/7432aac556065cc790d0527dc3852c1e63533e724aa33cfd65d9a6c62678d51b.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "7448dee54f7dd7e08c4e8831705f6006baf6e78b45d3f7ed3acc83f401bfd8a3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "505dc51e09f649da487b473c7c46d9f489924d2d5330582a14ee2271c44966ee", "generation_seconds_batch": 20.354350549983792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14240971207618713, "target_z": -0.24511719551122216, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.7355380058288574, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7448dee54f7dd7e08c4e8831705f6006baf6e78b45d3f7ed3acc83f401bfd8a3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "7531e680f01c267b8a660d5cad2e46afa6d58c629378a47c09671ceea9a5eacd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f24a91c0d138ca7e4103417b913f58924555d4ba929179ca223b3a3dae3edbd0", "generation_seconds_batch": 14.590224985033274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6763737201690674, "target_z": 4.343749878566737, "ce": 6.221180438995361, "genuineness": 4.124508857727051, "identity": 0.6502097845077515, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7531e680f01c267b8a660d5cad2e46afa6d58c629378a47c09671ceea9a5eacd.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "75dcf3606e9a639abef4f1aaf82b919e4606eef0b9ed92eb2df7128ed27615d8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d43d0d3dbb79c8499eb7d8974e4f86f1bfea8299c6506d009bfcb02b14380a47", "generation_seconds_batch": 16.486829448025674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968869924545288, "target_z": 3.062500080955508, "ce": 6.141753673553467, "genuineness": 4.21237325668335, "identity": 0.37800687551498413, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/75dcf3606e9a639abef4f1aaf82b919e4606eef0b9ed92eb2df7128ed27615d8.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": "7652f5f50e9efa334d1018de15bce0b5f8f8b23cd3e1ab2473c2eb7adbbf8cb0", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "961a5d40b46cd712fc30fdea47adf160c10625cfb2e367f6bedebb2c02c565b1", "generation_seconds_batch": 15.436860081041232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0033822059631348, "target_z": 3.1249998920593223, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.5718700289726257, "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_Astonishment_Surprise/7652f5f50e9efa334d1018de15bce0b5f8f8b23cd3e1ab2473c2eb7adbbf8cb0.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "76b09fab69ecbdb7b15d55ebd7ad6ac557d6e025b5b1637b9fad7ecd2062e225", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cc4e5cd9877264ff0bb185e8cf8069de3001015934ee174294ab1e733f32af21", "generation_seconds_batch": 17.410318601992913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.675514578819275, "target_z": 2.531249959522246, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.333068311214447, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/76b09fab69ecbdb7b15d55ebd7ad6ac557d6e025b5b1637b9fad7ecd2062e225.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "76b3ca6956452c4391f6b3d28464c792e83e6ddcbd758a864431a180bb3a92c6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "426ac7594d7bfe28a9803faf5f621391ce98a67a71332c7315b41c70fae40afc", "generation_seconds_batch": 21.95394108898472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6237460374832153, "target_z": 2.437500026985169, "ce": 6.038498878479004, "genuineness": 4.2374773025512695, "identity": 0.6200379729270935, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/76b3ca6956452c4391f6b3d28464c792e83e6ddcbd758a864431a180bb3a92c6.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "76ea171611153daa3013cc12824321a262a869b1d60762df0d16402b2bbee95b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d6b52b0e17d57bccc95edf21aaf2bd7374157b4d87eeb73c074af796e82c0c44", "generation_seconds_batch": 20.146875887992792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1276304721832275, "target_z": 1.5390624898805614, "ce": 6.062326908111572, "genuineness": 4.074300289154053, "identity": 0.6845632195472717, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/76ea171611153daa3013cc12824321a262a869b1d60762df0d16402b2bbee95b.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "a314afb74acb6d79d6968809cfc405ec20fd7b41315799fb653ac281acd96f88", "generation_seconds_batch": 16.43477197899483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6919115781784058, "target_z": 0.7499999460296612, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.7224935293197632, "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_Astonishment_Surprise/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77b54c884b5d5cd66c5e56e9b02ab1a191c4e608ab80107f005bec7023d03475", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f2fa86a8a544faea91a684e5f411b5d90b22f41e35ea7071e39a42dc6f673a62", "generation_seconds_batch": 16.07354987389408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3139936923980713, "target_z": 3.687499919044492, "ce": 6.292664527893066, "genuineness": 4.193545341491699, "identity": 0.21022263169288635, "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_Astonishment_Surprise/77b54c884b5d5cd66c5e56e9b02ab1a191c4e608ab80107f005bec7023d03475.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": "77b781f6f105d42d7d9dec496952a0bc0a62dd6b983c8bc989f9c5efabbc4186", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec299b33365f3efddb8c8b77deda3a7406bc8ad83372eb8a477b979b00d294d4", "generation_seconds_batch": 17.34405041008722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.088804006576538, "target_z": 1.4687499325370765, "ce": 6.229123115539551, "genuineness": 4.432034492492676, "identity": 0.6413710713386536, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lise-le bien et vérifie 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_Astonishment_Surprise/77b781f6f105d42d7d9dec496952a0bc0a62dd6b983c8bc989f9c5efabbc4186.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": "78886da03de08f891f611629e1ea8fcf1033845441694c761b7cc4106e92fde9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5720c3a1b30990432f0548f01dfdd554ca1616c1e0ac8dd40276e9cface1a506", "generation_seconds_batch": 14.56160689110402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7971670627593994, "target_z": 4.5624998650741535, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.7119055986404419, "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_Astonishment_Surprise/78886da03de08f891f611629e1ea8fcf1033845441694c761b7cc4106e92fde9.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "af542e9bb2d7cccf0e2ffdb3bc16b799cf50c3de40a828432f4765103a596022", "generation_seconds_batch": 16.934857374057174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2809985280036926, "target_z": 0.005859397768736667, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.7833386659622192, "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_Astonishment_Surprise/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "795ea49de8992766f0dfb43d0dcd7cbf2681eb0bc012fbed671efb42e2d8f47c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ddaf9c20c3e2ea0e3d4a781b3caf3b5fea97f4e51a7228a5cf3784c7aa0125b", "generation_seconds_batch": 21.01079299999401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04049032926559448, "target_z": -0.42968749662685385, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.5848211646080017, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/795ea49de8992766f0dfb43d0dcd7cbf2681eb0bc012fbed671efb42e2d8f47c.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "7984de134d1e656d3f79293c1eda58ee1f44db1cb33c8a23c7c832cbf69a8081", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3469b0141e2c37805b3b6e4d7e5f804d3fddd482aeda9ed3711de02a85cea950", "generation_seconds_batch": 20.690998382982798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847217321395874, "target_z": 1.031249959522246, "ce": 6.046441555023193, "genuineness": 3.773050308227539, "identity": 0.5074292421340942, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7984de134d1e656d3f79293c1eda58ee1f44db1cb33c8a23c7c832cbf69a8081.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "7a1ecc40b8af5eadc999a6df22474c47168eba2c75ce108b67987e947b74480c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5bda2ef22f035ad102f7a1c6b147fd04200bb6f81bba314b96b7cad2af6d8493", "generation_seconds_batch": 23.361487068003044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0551507472991943, "target_z": 3.218749824596399, "ce": 5.895530700683594, "genuineness": 3.9676074981689453, "identity": 0.3779980540275574, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7a1ecc40b8af5eadc999a6df22474c47168eba2c75ce108b67987e947b74480c.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "7a3beae6d7bd7903c9799009273385463611481e238e4bbdb132df5c49ceb165", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "06bad5054ddd6b92836528dd64704bdba6e53ddaee6e3f9b475d15d80940fb48", "generation_seconds_batch": 15.166599130025133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.727283239364624, "target_z": 2.6250001079406777, "ce": 6.109982967376709, "genuineness": 4.15588903427124, "identity": 0.7224035859107971, "hypothesis": "De tor 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_Astonishment_Surprise/7a3beae6d7bd7903c9799009273385463611481e238e4bbdb132df5c49ceb165.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "7a59071925d71e69b258c29f2daa1009af5f98307fd6218ea648bc8a940c4c54", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "113f6ed710e8518d8ae27f31bab49f3994ccf72318d21db00468256008b9ebb5", "generation_seconds_batch": 22.710137857007794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1595470905303955, "target_z": 5.218749824596399, "ce": 5.982900142669678, "genuineness": 3.8797430992126465, "identity": 0.4686482548713684, "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_Astonishment_Surprise/7a59071925d71e69b258c29f2daa1009af5f98307fd6218ea648bc8a940c4c54.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "7a98ab015481dfca87501c36f04f809cf6501822776423a05a970e1c6adc141c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5ab0cf451a2c92605de236d35ff66104960b61b4abb99df299f8cd9a8c92a6c", "generation_seconds_batch": 23.123010474955663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8653327226638794, "target_z": 2.875, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.5527244806289673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7a98ab015481dfca87501c36f04f809cf6501822776423a05a970e1c6adc141c.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "7b3a61e7773a73b257398e20b9529f1aa5e5ab6f4bae1f09e8b94a526745f6ba", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "41afc11db39645529c91f009633bc90da38542e1dfd202549177b6227a79b4d6", "generation_seconds_batch": 23.40570690704044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5806056261062622, "target_z": 2.3593751551647237, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.4630861282348633, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7b3a61e7773a73b257398e20b9529f1aa5e5ab6f4bae1f09e8b94a526745f6ba.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "7b6b115f7f86d5187d87e23231945051d672364912ab77e8466634abeb18f4d9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5db912ee5c1d98c78bea04c3e53d384232731077fedbd846f50e9de1788d8238", "generation_seconds_batch": 20.355297229951248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6228868365287781, "target_z": 0.625, "ce": 5.8875885009765625, "genuineness": 4.469690799713135, "identity": 0.713263213634491, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7b6b115f7f86d5187d87e23231945051d672364912ab77e8466634abeb18f4d9.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "7b815aa21e1c7034c6ca3e314c43cd8bc02a4abb08b04c4dad398a243565bb28", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "97fb37b42d9a76a3ca9d330e3148f024d7d6cf326c1ef583ee49f064201918fc", "generation_seconds_batch": 22.08696387906093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.589233636856079, "target_z": 2.375, "ce": 5.871703147888184, "genuineness": 3.8797430992126465, "identity": 0.3756980895996094, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7b815aa21e1c7034c6ca3e314c43cd8bc02a4abb08b04c4dad398a243565bb28.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "7bbd52f4204b0a0aa88cf454fd9f62f75b43adcf37e5a709b5338951a0924530", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1234ba24b7fe63023220593755edc64d487a1e23210c5b323c5dd389dbebb074", "generation_seconds_batch": 20.63235355296638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9291843175888062, "target_z": 1.1796876045675313, "ce": 5.895530700683594, "genuineness": 4.545003414154053, "identity": 0.6702900528907776, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7bbd52f4204b0a0aa88cf454fd9f62f75b43adcf37e5a709b5338951a0924530.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "7bf2246234aff4623da0a7d2452f6ef42d467178bccbb893918b9dbcde6b3550", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a1db38b44537ee909d75263e60be7635a18a1ef5ce706127f4d9d5944795027", "generation_seconds_batch": 22.220952814095654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.210456609725952, "target_z": 3.500000053970339, "ce": 6.022613525390625, "genuineness": 4.13078498840332, "identity": 0.4184704124927521, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7bf2246234aff4623da0a7d2452f6ef42d467178bccbb893918b9dbcde6b3550.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "7c17574b1c4a9e57036f9959224593980b58fe0a9d9c71cbcbd40a22165d9d3f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "88e39b9e01594ce2e20aa805db0f47e391ec94cfaaa77085759d3dd63e60b0c8", "generation_seconds_batch": 21.61612341296859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907874822616577, "target_z": 2.0156251146869697, "ce": 6.467403411865234, "genuineness": 4.2249250411987305, "identity": 0.6454708576202393, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7c17574b1c4a9e57036f9959224593980b58fe0a9d9c71cbcbd40a22165d9d3f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "7c4209b3c6dd75fc6dbdce5de5c9ff230f5213b1a2835cf238190d4016b37b94", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c3a32213361f54fdea1e3bb9b2a5040cac897ab0f3d693785507f5f2bedabd09", "generation_seconds_batch": 29.144100747071207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08147378265857697, "target_z": -0.35546875505971925, "ce": 6.260893821716309, "genuineness": 4.3127899169921875, "identity": 0.3576223850250244, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7c4209b3c6dd75fc6dbdce5de5c9ff230f5213b1a2835cf238190d4016b37b94.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "7cd0779b378ec436eb0c860d18524f1f74a52b745735404eacbcfe288d196636", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bd97b20821b1a9ecebd32ae3a717ad677a7decd2b0fc799a076f8349750a87d4", "generation_seconds_batch": 22.985311067081057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8860437870025635, "target_z": 1.1015625168657308, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.7209725379943848, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7cd0779b378ec436eb0c860d18524f1f74a52b745735404eacbcfe288d196636.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "7d38b276d06af623507c7a5cf858ce7aab633c907ea358cf6fd031417bae610f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8749d3828615261ab42659174818a6f5ca8815fb23aed6264daae36f358f3ecf", "generation_seconds_batch": 16.824962325044908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3433328866958618, "target_z": 1.9296874966268538, "ce": 5.792276382446289, "genuineness": 3.9550557136535645, "identity": 0.4185982048511505, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7d38b276d06af623507c7a5cf858ce7aab633c907ea358cf6fd031417bae610f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "7d8368694bd5f656ba8a0d2759df21120ddc0f574de2c35c16b53bf9f1c53523", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e003e3d5c20ce03c2218e3085c0f3714c28aaabade1dabbf18d0022880250aa3", "generation_seconds_batch": 21.589569165953435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4244406223297119, "target_z": 0.26562500674629236, "ce": 6.260893821716309, "genuineness": 4.607763767242432, "identity": 0.7519537210464478, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7d8368694bd5f656ba8a0d2759df21120ddc0f574de2c35c16b53bf9f1c53523.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "7e0822a3af3141493091e3be465cfe8c05b583196470d73fc1543b8c8e2682d5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d87884a20da3f3f6444d004d8177569d9c224f03be011567ca64def8f942f2aa", "generation_seconds_batch": 22.08696387906093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8049360513687134, "target_z": 2.7656250067462924, "ce": 5.974957466125488, "genuineness": 4.017816066741943, "identity": 0.5765131115913391, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7e0822a3af3141493091e3be465cfe8c05b583196470d73fc1543b8c8e2682d5.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": "7e155e6d90137908212d07b9602702f73d71cb0f8f3edb68ea6a0c04000a3f54", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "70758620dbf16347b1eb8bd497c759b92dd0910d3ff57548f09b8a79950980a0", "generation_seconds_batch": 19.41039783100132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.004241466522217, "target_z": 4.93750002698517, "ce": 6.125868320465088, "genuineness": 4.2249250411987305, "identity": 0.43197616934776306, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7e155e6d90137908212d07b9602702f73d71cb0f8f3edb68ea6a0c04000a3f54.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": "7ec6fc2101a9c90c3dace24bf4f2aa82710854d5a538996a69774a1c21c42b94", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d35d0f853115e4321b6098cacdbed051bad601b9e70804d19c54ac863252b9e7", "generation_seconds_batch": 21.347534024040215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2009693384170532, "target_z": 1.6718750742092159, "ce": 6.141753673553467, "genuineness": 4.055472373962402, "identity": 0.3478444516658783, "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_Astonishment_Surprise/7ec6fc2101a9c90c3dace24bf4f2aa82710854d5a538996a69774a1c21c42b94.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": "7f513b59c175f4ebdab289a521a68e93a2e7af653d9b36e76cfca0d48e57e524", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6da8713aec6187f21c5f2e6b3875ae057ae16ed8089e3b872b22fff8d65f4265", "generation_seconds_batch": 16.63207096804399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44601085782051086, "target_z": 0.30468749662685385, "ce": 5.990842819213867, "genuineness": 3.9425034523010254, "identity": 0.7201941013336182, "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_Astonishment_Surprise/7f513b59c175f4ebdab289a521a68e93a2e7af653d9b36e76cfca0d48e57e524.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "81c129e5c58a102979ba5e34e0acfe0354a65bbf2894d63b8c5f1d0b15def25f", "generation_seconds_batch": 14.727747478988022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3672794699668884, "target_z": 0.16210935729098258, "ce": 6.419747352600098, "genuineness": 4.557555198669434, "identity": 0.11287553608417511, "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_Astonishment_Surprise/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "7f8dcad0bc50ed80a8b238415fafe14ca48afda4376a3b2dbce367abef648935", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cf137345e02d1bad0fd35f45aa8fb23d7820442657cc6e2b7442d1e2f55f4de3", "generation_seconds_batch": 24.215149392955936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9343575239181519, "target_z": 3.000000053970339, "ce": 6.078212261199951, "genuineness": 3.6663577556610107, "identity": 0.5337409377098083, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7f8dcad0bc50ed80a8b238415fafe14ca48afda4376a3b2dbce367abef648935.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "7ff7c9d9edd121e7a5539875422d75a117f96576978a472e79eb0df752a36da8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "495ebba0c95795d7ff66d3385523f469883a010560610d82ac2829d65effd654", "generation_seconds_batch": 20.355297229951248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48699432611465454, "target_z": 0.37890626517915776, "ce": 6.022613525390625, "genuineness": 4.369274139404297, "identity": 0.6215780377388, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7ff7c9d9edd121e7a5539875422d75a117f96576978a472e79eb0df752a36da8.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "7fff69388bb78a1718d1a7a6f19f9b313f7d68ba1e93f650a412807ff29899aa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "05da013dc6eb7e1fa0ddc2d9c56585979fd21ee88523940a417c8163c7add1a3", "generation_seconds_batch": 23.23453816806432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9343575239181519, "target_z": 3.000000053970339, "ce": 6.268836498260498, "genuineness": 4.375550270080566, "identity": 0.5130012631416321, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/7fff69388bb78a1718d1a7a6f19f9b313f7d68ba1e93f650a412807ff29899aa.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "808d91e54b8c23c385f840c1f78cc47db78e5864faf0f50007c84f531f09a641", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "390b24069b8db5ac1e32b9a230bcb7eb6bc0f6f2d3ce562e358272545052dea5", "generation_seconds_batch": 15.707480504061095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.309579074382782, "target_z": 0.05761716852605278, "ce": 6.356205940246582, "genuineness": 4.15588903427124, "identity": 0.46370816230773926, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/808d91e54b8c23c385f840c1f78cc47db78e5864faf0f50007c84f531f09a641.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "1f06179a6e5b137abff51835727088f6d2b643eaf9a2f373ab050f85a1235f0e", "generation_seconds_batch": 15.171072655008174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4697381258010864, "target_z": 0.3476562516865731, "ce": 6.316492557525635, "genuineness": 4.444586753845215, "identity": 0.6144059896469116, "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_Astonishment_Surprise/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "81710eaf2e60b558f9fb440d22e92b0dd244ed841fdcf7de72e018c7dbffa0a3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4aa05d4eda6e4338931d0f50dbaadc6b2e236293bbe34ce0e458cd62e69168be", "generation_seconds_batch": 16.1252463349374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0387537479400635, "target_z": 4.999999838088984, "ce": 5.982900142669678, "genuineness": 3.9173994064331055, "identity": 0.30469757318496704, "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_Astonishment_Surprise/81710eaf2e60b558f9fb440d22e92b0dd244ed841fdcf7de72e018c7dbffa0a3.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "81aa9341dd07ca3ed4effdb9431600a8ab400ff376d0a20aec2c8f7460bb0702", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a215a8f65a36cdc9aa3268fb8510624ce08617db4bbdaa9c179c67b41d789f5", "generation_seconds_batch": 22.736944678938016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5603331327438354, "target_z": 0.5117187415671346, "ce": 6.1020402908325195, "genuineness": 4.419482707977295, "identity": 0.5154114961624146, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/81aa9341dd07ca3ed4effdb9431600a8ab400ff376d0a20aec2c8f7460bb0702.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "81addbda36917fe70a8be10b3c9a6e27a1a3d8afaf0b8eb3d5a780662056f1f7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9df0345f137d4e2e752c3206fdffd53de61cf702ebec74390e5646155963d6bc", "generation_seconds_batch": 23.040852318052202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1650584638118744, "target_z": -0.20410157304108179, "ce": 6.141753673553467, "genuineness": 4.595211505889893, "identity": 0.6368280649185181, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/81addbda36917fe70a8be10b3c9a6e27a1a3d8afaf0b8eb3d5a780662056f1f7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "81d3d3dfd41a6180681d2f77e31772ead3244ddeec1bc5961d641c173ba6ef87", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f8f9ba0fd526b196817113d715bd127047c5676a7f514bd7e7f6744488a4c4c3", "generation_seconds_batch": 24.935629420913756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1422908306121826, "target_z": 5.1874997031631365, "ce": 5.804190158843994, "genuineness": 4.005263805389404, "identity": 0.6014283299446106, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/81d3d3dfd41a6180681d2f77e31772ead3244ddeec1bc5961d641c173ba6ef87.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "81e243d6b2fb4f8ec6bf8f0b65601548872ea37e7211d2b13dc6ce4f662169f6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f269daf25d5e87350493772d776016bca67da7c60cec4ab2ac1e5c555e2edaf4", "generation_seconds_batch": 24.37243606999982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.226853609085083, "target_z": 1.718750040477754, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.7358404994010925, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Hmm.", "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_Astonishment_Surprise/81e243d6b2fb4f8ec6bf8f0b65601548872ea37e7211d2b13dc6ce4f662169f6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "827cbcdc10394c640a28363ae5ff3a74bf37356e28f985cf5330b535df9deb5e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8dbeafac59c40537f8f63777777ed2cdec5fa50875a84231918d6823da4403fd", "generation_seconds_batch": 17.201127987005748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.985266923904419, "target_z": 1.2812500674629235, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.7041486501693726, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la lacius, 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_Astonishment_Surprise/827cbcdc10394c640a28363ae5ff3a74bf37356e28f985cf5330b535df9deb5e.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "834d50ea1c506c87edcc39a4cd7b975c6923cabfb217d17ddf5bc27ea3c6f7bb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5e7bb5678370237a635646ed0b8c8fadd8e12325c4d012678784da1618c68198", "generation_seconds_batch": 23.26949869201053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1923412084579468, "target_z": 1.6562500134925846, "ce": 6.046441555023193, "genuineness": 4.13078498840332, "identity": 0.5877472162246704, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/834d50ea1c506c87edcc39a4cd7b975c6923cabfb217d17ddf5bc27ea3c6f7bb.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "83679cbc3f3f9087f4a9e120f587438b078ca82470a8dc3f25519ce330ca70d8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23f45b271c34e8fd741ed5b4865a06ad2268db3d7464d795406761f3733b7e2e", "generation_seconds_batch": 19.72402574401349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5862174034118652, "target_z": 0.5585937078356729, "ce": 6.41180419921875, "genuineness": 4.557555198669434, "identity": 0.45852816104888916, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/83679cbc3f3f9087f4a9e120f587438b078ca82470a8dc3f25519ce330ca70d8.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "83f57484d879d3a34c3f8fc4d6be9a2d5dd8ee3455f4efd070ecfccaa2d27ec7", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e98c5dde4af613a9492c29d449f701c844478240303682c475780421736ef2f3", "generation_seconds_batch": 16.307427919004112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02539116144180298, "target_z": -0.45703124494028075, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.6209196448326111, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/83f57484d879d3a34c3f8fc4d6be9a2d5dd8ee3455f4efd070ecfccaa2d27ec7.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "84ccdafda07dfcd2a4c4391897dcdd6fb7040a3a3e57f557e6637b9dd674e8cb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "878bd6ce35715fe646f631665ee600da4b9e209307e8aa36b56bc6e7a5c9b5d1", "generation_seconds_batch": 23.220049284980632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2648208439350128, "target_z": -0.023437483134269136, "ce": 6.205295085906982, "genuineness": 4.507347106933594, "identity": 0.6626060009002686, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/84ccdafda07dfcd2a4c4391897dcdd6fb7040a3a3e57f557e6637b9dd674e8cb.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": "857b0c80d3a179ddc65937aaeffd7034cae8d3449563cc010c962e09f3fd1990", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee93624782e3d86a3c0abe9b3d45c5c216c64d381f11dfbb13aab19fc41b4a03", "generation_seconds_batch": 16.64591131301131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6315149068832397, "target_z": 0.6406249527759535, "ce": 6.205295085906982, "genuineness": 4.042920112609863, "identity": 0.3326731026172638, "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_Astonishment_Surprise/857b0c80d3a179ddc65937aaeffd7034cae8d3449563cc010c962e09f3fd1990.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "85b1920d3d06ab768152cd3ecedfacfd76b5d1629ee1b46c76b7058916b78dee", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4b6562c0c4d8999e8108b0e9aa3b11e2a9b1e88fd9f8a591e2035ecacb79d859", "generation_seconds_batch": 23.40570690704044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9119280576705933, "target_z": 1.1484374831342692, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.24483422935009003, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/85b1920d3d06ab768152cd3ecedfacfd76b5d1629ee1b46c76b7058916b78dee.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "85b69c79a11c1e197f769d631ae20ee4c5d3220dda27a4fd1bfb1e2dce3bc198", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4a315e91c0a6d65a0af3e2d7ee3ae7ff24a03769d947b8d0fd97bf9c499c2111", "generation_seconds_batch": 22.92729001690168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0197793245315552, "target_z": 1.343750094448093, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.4828362464904785, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/85b69c79a11c1e197f769d631ae20ee4c5d3220dda27a4fd1bfb1e2dce3bc198.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": "85c517e8ac877ce7f60ad2c0444fb1c4f8e50dd60444e0e9f228f959da005cba", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cb8237cfeca0ff7693199ada565402093df6d014d5107c173b24d5a2690517f7", "generation_seconds_batch": 20.827095576096326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9636965990066528, "target_z": 1.2421874156713457, "ce": 5.982900142669678, "genuineness": 4.099404335021973, "identity": 0.6132910847663879, "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_Astonishment_Surprise/85c517e8ac877ce7f60ad2c0444fb1c4f8e50dd60444e0e9f228f959da005cba.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "8646da1e6d165217d7e394c30e76fc924d5cca3abfbbe0f1fa83702e8e4c264c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "03e98af8e4d42fa9341ef9f071e885e29a7d980e312d3fe8193c39d06045b898", "generation_seconds_batch": 15.815911814919673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1319445371627808, "target_z": 1.546875020238877, "ce": 6.443574905395508, "genuineness": 4.444586753845215, "identity": 0.457874059677124, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8646da1e6d165217d7e394c30e76fc924d5cca3abfbbe0f1fa83702e8e4c264c.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": "864ba15c039d5b81b60b348ba22af1183ad8cbaa97b3ad6d913165631db0b26a", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31a107b891062f188d0e20b335ebd570c8e6415ec046934ee799ad1d4f683ba3", "generation_seconds_batch": 14.43047717702575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6228868365287781, "target_z": 0.625, "ce": 6.324435234069824, "genuineness": 3.9425034523010254, "identity": 0.48998528718948364, "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_Astonishment_Surprise/864ba15c039d5b81b60b348ba22af1183ad8cbaa97b3ad6d913165631db0b26a.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "87083c45551575137d73094cf5e6cc4cdd837f3b812a12742676c12be62f74c1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7aa698e548794bd8b10e08a7c0026c80b5c1471b934561e1487ba3204cef48bb", "generation_seconds_batch": 16.71587846602779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4503248929977417, "target_z": 0.3124999730148306, "ce": 6.292664527893066, "genuineness": 4.344170093536377, "identity": 0.5200794339179993, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/87083c45551575137d73094cf5e6cc4cdd837f3b812a12742676c12be62f74c1.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "875e2abb8d28f91284453c6f94e8b448388fcf27cedc742da8f93757344a1d37", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a79c34e22b3c1f85e811011cbbeeeaa2b6004a077e48a762f5b9283ec5f05aa7", "generation_seconds_batch": 20.696922120987438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.624605178833008, "target_z": 4.249999946029662, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.5818793177604675, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/875e2abb8d28f91284453c6f94e8b448388fcf27cedc742da8f93757344a1d37.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "87905a35f60a0391369faa7bb0936245f64a485fdb4d0b821b9f8326dbbcf3d0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9fbf1d8a83233ab65cfc109fab5c5a9fd632e5d628ad5119799fedfbc7208a1b", "generation_seconds_batch": 15.990324640995823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9774980545043945, "target_z": 3.0781251416721394, "ce": 6.181467056274414, "genuineness": 4.369274139404297, "identity": 0.48784780502319336, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/87905a35f60a0391369faa7bb0936245f64a485fdb4d0b821b9f8326dbbcf3d0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "87a463e05de77ad464bf6f50fdd074948bb7fc8552a3fe89ff42e169255f0470", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d054691fc3f7b5806080f7e70b3fe5c4c1460e08942376b11d6e5bb2f2224191", "generation_seconds_batch": 22.352931184927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19256052374839783, "target_z": -0.1542968809030058, "ce": 6.086154937744141, "genuineness": 4.758388519287109, "identity": 0.762493908405304, "hypothesis": "J'ai trouvé la petite pote. 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_Astonishment_Surprise/87a463e05de77ad464bf6f50fdd074948bb7fc8552a3fe89ff42e169255f0470.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "87b092a16a19c6b8eae3774faf0232a40af60c940bae8af78f479725f6458aaf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b6f82b1d72c44d07980536cda6a018b3ede8dfc7031a7f1a970e1666d456901b", "generation_seconds_batch": 17.94848587096203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3217626810073853, "target_z": 1.890625060716631, "ce": 5.863759994506836, "genuineness": 3.6789097785949707, "identity": 0.5128899216651917, "hypothesis": "The 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_Astonishment_Surprise/87b092a16a19c6b8eae3774faf0232a40af60c940bae8af78f479725f6458aaf.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "87d76a6d0c4a84ce24b33a0cbd7c86760a46a9b7abda84236954e74da1e2bbf7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4b8e1ba5c88b4085093c2b412e0063b1c6c249d3eab86b1e8991dcbda52d016c", "generation_seconds_batch": 23.344896973110735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.866191864013672, "target_z": 4.687499919044492, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.4874367117881775, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/87d76a6d0c4a84ce24b33a0cbd7c86760a46a9b7abda84236954e74da1e2bbf7.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "8859e95ffddc8bc6b93cddda4cd39c9cea0ac3bae34aaaebcd6b3baeb2392efc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5d5ed61fb9a4faee466a9b9c11c1ce8c7e26a9a215adf75e75a199329dd3b6fb", "generation_seconds_batch": 23.545835557975806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.831679344177246, "target_z": 4.624999676177968, "ce": 6.125868320465088, "genuineness": 4.1998209953308105, "identity": 0.39883720874786377, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8859e95ffddc8bc6b93cddda4cd39c9cea0ac3bae34aaaebcd6b3baeb2392efc.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "88bf49e5d2318cf54ba6d424d41bac49bcf94df41b43d11e64066a635f56a066", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7156c2ae149b55bf8011300e00bf36ff90844f14a4b42e25c80a7793c88ef12e", "generation_seconds_batch": 23.23453816806432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3226218223571777, "target_z": 3.7031249797611228, "ce": 6.252951145172119, "genuineness": 4.143336772918701, "identity": 0.48064208030700684, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/88bf49e5d2318cf54ba6d424d41bac49bcf94df41b43d11e64066a635f56a066.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "88e8bbd207731bf8dcac471f09feddac17dbb674d7915861e42bf683ff4fe97f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ef0497e58ef854c9c62d471678460d48743269e10ead5bb0a999b9f09058a236", "generation_seconds_batch": 16.974026051000692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.486555576324463, "target_z": 3.999999838088984, "ce": 5.990842819213867, "genuineness": 4.124508857727051, "identity": 0.543999195098877, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/88e8bbd207731bf8dcac471f09feddac17dbb674d7915861e42bf683ff4fe97f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "89057c14bbf1efcaf2326fc9f6ce52312cebb57501a1ef702e1b0b9449ad9fba", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1dcd0c924f4bd29e2046b1fb6b19e57f947685bf9c587d8ed05a0236c938ba39", "generation_seconds_batch": 20.713296809000894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7177959084510803, "target_z": 0.796875020238877, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.7845659852027893, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/89057c14bbf1efcaf2326fc9f6ce52312cebb57501a1ef702e1b0b9449ad9fba.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "89409e1616366bc88e98627e974fc36f6094a37d02fa8995cfb283b48686b22a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e0c5e9f3e3733c29db0859359db3a7dc3f81711cdfc9a865389c7666648cee7f", "generation_seconds_batch": 20.091293392004445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7971670627593994, "target_z": 4.5624998650741535, "ce": 6.117925643920898, "genuineness": 4.017816066741943, "identity": 0.6644478440284729, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/89409e1616366bc88e98627e974fc36f6094a37d02fa8995cfb283b48686b22a.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "89648854f111d5ab8f16cda2c5bf5bd019a0379d91b8433b0f5192733bd5bf35", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8b86cbc1ed9038b190ac6c2a7edfe37ab640e82805f492c244305c75452a1e98", "generation_seconds_batch": 16.47373189695645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.487414836883545, "target_z": 5.81249997301483, "ce": 5.561938762664795, "genuineness": 3.7416701316833496, "identity": 0.017597174271941185, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/89648854f111d5ab8f16cda2c5bf5bd019a0379d91b8433b0f5192733bd5bf35.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "89b287f40fe39dc364da7536618ea0f6fe2d8012808bf4c1093c1fdfe0c29fed", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "38ab72c14f7fbccfdc8cec1a453b12e8d5e262029aba19156713347da9a685ec", "generation_seconds_batch": 16.96989339601714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49022984504699707, "target_z": 0.3847656089775557, "ce": 6.427689552307129, "genuineness": 4.331617832183838, "identity": 0.3297683000564575, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/89b287f40fe39dc364da7536618ea0f6fe2d8012808bf4c1093c1fdfe0c29fed.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "89d0e3536df3ab17af6cef2e480daa5ae8e62d3a40875f09a2b39a007ea15f26", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3d71a82c66ebf8338476f45dfd1676767ad5ab11cc2624f998f4296898dab4b5", "generation_seconds_batch": 22.72283869201783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4511841535568237, "target_z": 2.1250001079406777, "ce": 6.24500846862793, "genuineness": 4.218649387359619, "identity": 0.6570634841918945, "hypothesis": "Ik heb het klein 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_Astonishment_Surprise/89d0e3536df3ab17af6cef2e480daa5ae8e62d3a40875f09a2b39a007ea15f26.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "89f955f937b3670f93718c990febf0865105f9af73111a997fd3dd7ae17f02bf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5a24180af1a540457f2d29c398305e946f1607d26ff6429ef64354a1723ac84", "generation_seconds_batch": 16.29615479707718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5555803775787354, "target_z": 4.124999892059322, "ce": 6.022613525390625, "genuineness": 4.18099308013916, "identity": 0.5530900955200195, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/89f955f937b3670f93718c990febf0865105f9af73111a997fd3dd7ae17f02bf.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "8a0b8cda46f480da7bbe739ed6ee397493e8e7388eab89ca2d3c7ff12c468604", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "df271eed5bba5a3f7dd15bfecdc11d27eaba7dd69378210e00e9eca805572a08", "generation_seconds_batch": 21.38025987497531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0033822059631348, "target_z": 3.1249998920593223, "ce": 6.038498878479004, "genuineness": 4.231201171875, "identity": 0.4902955889701843, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8a0b8cda46f480da7bbe739ed6ee397493e8e7388eab89ca2d3c7ff12c468604.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "8b4561ac5a265abc05acc0fa4cdbaf13caf8bc24d0547c21cbe2411a6add36ec", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "343e5df789a3e5c78c13ae505dab7a56de74deb5dce1f84eea33b6314393862b", "generation_seconds_batch": 20.353434497956187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5029526948928833, "target_z": 2.218750040477754, "ce": 6.173524379730225, "genuineness": 4.319066047668457, "identity": 0.48840445280075073, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8b4561ac5a265abc05acc0fa4cdbaf13caf8bc24d0547c21cbe2411a6add36ec.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "8b85a240a79ce5ed144d4cb907a0c4639f6053d030d3cded0cd82e1b17852ca5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8bffbef30f74267886d7a09fe08e0bccdad5f7f991e8dfceb0bdd87a2d4abc79", "generation_seconds_batch": 22.87103564699646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4665026068687439, "target_z": 0.3417969078881752, "ce": 5.959072113037109, "genuineness": 3.9801597595214844, "identity": 0.35788023471832275, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8b85a240a79ce5ed144d4cb907a0c4639f6053d030d3cded0cd82e1b17852ca5.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "8bc6c08c7d8cba6a357c9981bf5cb4629cdfa634fc571235fe893825a6dde09b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ae31f4d5d0abc3883f7e6c31c31fc292d12398998c8f46b62fdfaebb8b11c36c", "generation_seconds_batch": 22.84544134803582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5862174034118652, "target_z": 0.5585937078356729, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.3755195736885071, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8bc6c08c7d8cba6a357c9981bf5cb4629cdfa634fc571235fe893825a6dde09b.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "8c40c1d99bd6dc020da2e54097aa4f735ab492076f67e2173224333d6ac60bea", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c2771cc2d175ff9646457f7eec7b27cba05e64ae617498ae4950e6fac8b9630b", "generation_seconds_batch": 22.58347586391028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.305365562438965, "target_z": 3.6718748583278606, "ce": 6.24500846862793, "genuineness": 4.149612903594971, "identity": 0.6109598875045776, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8c40c1d99bd6dc020da2e54097aa4f735ab492076f67e2173224333d6ac60bea.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "8c4c90bb389a4df7c341ddfaeb5d965af4b25415c81c434cb324b2a456ce65cb", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "675438f36b553ef244639037038cf8913b12105221b52fb006af2ace18dd22a3", "generation_seconds_batch": 15.807827395037748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12030021846294403, "target_z": -0.2851562516865731, "ce": 6.109982967376709, "genuineness": 4.168440818786621, "identity": 0.5842270255088806, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8c4c90bb389a4df7c341ddfaeb5d965af4b25415c81c434cb324b2a456ce65cb.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "8c881c89d16baf210d109a46c22c291efa66a05bdb7ebfe2146a8f08fd61eb66", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "30e5ba71e9ccd88105adfe5cbe9458194cbe5d7a1a42595ec43fa692ca04ff82", "generation_seconds_batch": 22.92729001690168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3839964270591736, "target_z": 0.19238283147394722, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.6443130373954773, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8c881c89d16baf210d109a46c22c291efa66a05bdb7ebfe2146a8f08fd61eb66.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "8d0c24927d30f37012082a21b23a38c217ad66f77ce985baf2be0b713c703ba7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "26d4892c7529aa892ce952e4f8ed6bd0831c2c0520bed61de97f97bcc2538c88", "generation_seconds_batch": 21.41529958997853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968869924545288, "target_z": 3.062500080955508, "ce": 6.09409761428833, "genuineness": 4.124508857727051, "identity": 0.5991240739822388, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8d0c24927d30f37012082a21b23a38c217ad66f77ce985baf2be0b713c703ba7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "8d643fad12a58b1f3c2982dc176c57e88fe3393f800c64b22cd2a434621a4ae3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "87fc99de8965ff95de522617f7ef282db15ff5968213e1776837d8337f9e2360", "generation_seconds_batch": 23.105600110953674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23462249338626862, "target_z": -0.07812500674629234, "ce": 6.046441555023193, "genuineness": 4.595211505889893, "identity": 0.5516418218612671, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8d643fad12a58b1f3c2982dc176c57e88fe3393f800c64b22cd2a434621a4ae3.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "8db21d5745b349f6b03c9406011c54a4165be02b5ad0a6fa02e5b6c45c9ba3c2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9023265388b1afcbcea0502e6508911fff97a56d6d5572e133ba70af9e0e9ef4", "generation_seconds_batch": 22.743080928106792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.468440294265747, "target_z": 2.156250013492585, "ce": 6.2767791748046875, "genuineness": 4.356721878051758, "identity": 0.5575520992279053, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8db21d5745b349f6b03c9406011c54a4165be02b5ad0a6fa02e5b6c45c9ba3c2.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "8dfdb8671a2c60f96a0ad1ad0dc0dd623db49fbf23232b6ddb778369c57ef4fd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "14b2ee3382934fed81b514c3ccc19b282048cfa12e6fa63b8cd36ea061b58c79", "generation_seconds_batch": 22.086081599001773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.44231095910072327, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8dfdb8671a2c60f96a0ad1ad0dc0dd623db49fbf23232b6ddb778369c57ef4fd.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "8dffa51fa9ea8d92950a4208a9310910fcc167f113c3f3397d1210155a5db0c3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8aeb0fc235d93e310cbd12a55a78693fb2b88758bdeb9dc4543c12c6a07a523e", "generation_seconds_batch": 22.174740009009838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.726423978805542, "target_z": 0.8124999730148306, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.6431052684783936, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8dffa51fa9ea8d92950a4208a9310910fcc167f113c3f3397d1210155a5db0c3.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": "8e52141898c6acc6380e302410662ec410d49999e1a482e7e0151293f6bb016f", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "836c01639401480ef2ce01f5c843629b3031aae3d7bc14fa2aaf63da82b7bfda", "generation_seconds_batch": 16.24778040498495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 6.062326908111572, "genuineness": 3.9927117824554443, "identity": 0.8091241717338562, "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_Astonishment_Surprise/8e52141898c6acc6380e302410662ec410d49999e1a482e7e0151293f6bb016f.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "8e684ba24468471c01f80dc3175efa1b60d52aebfa0cd2740bbeec6ce39d4923", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e23dc58daad54cff28db2495bad57d24a6b7003b4cca6f27bee209dad8e4b98", "generation_seconds_batch": 21.055848810006864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.245828151702881, "target_z": 5.375, "ce": 5.982900142669678, "genuineness": 3.7291181087493896, "identity": 0.5058307647705078, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8e684ba24468471c01f80dc3175efa1b60d52aebfa0cd2740bbeec6ce39d4923.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "8e7e72b3578d23e2e0b75b29c4d0ca73b5149bd8fb8ab0b94539c1861155ddfa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f567a00ff736ae4b5e63c8255ffd6c1abc7b3bb076c7d6c99cde625b80669001", "generation_seconds_batch": 19.835043646977283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3303404450416565, "target_z": 0.09521484944218417, "ce": 6.1894097328186035, "genuineness": 4.319066047668457, "identity": 0.8089758157730103, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8e7e72b3578d23e2e0b75b29c4d0ca73b5149bd8fb8ab0b94539c1861155ddfa.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "8ecd92a7f3defc3e749914607d5bf0d361cf680adc75852188826d48a523d683", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "279e2849b1e3364c23fdf97de3874c2ead5aff319a3767f0d69a49486986b395", "generation_seconds_batch": 22.18526918592397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.085787832736969, "target_z": -0.3476562516865731, "ce": 6.292664527893066, "genuineness": 4.519899368286133, "identity": 0.6563369035720825, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8ecd92a7f3defc3e749914607d5bf0d361cf680adc75852188826d48a523d683.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "8ed054ff7cf1d91565c521662aaac30a9826624acc6905ea38df17409b60d5cc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2d61ab1d3bbd4baa4e695f0545660d3f04c51d18034ebebf219a81eef399a911", "generation_seconds_batch": 19.41194987401832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17853987216949463, "target_z": -0.17968749662685382, "ce": 6.125868320465088, "genuineness": 4.406930446624756, "identity": 0.35801270604133606, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8ed054ff7cf1d91565c521662aaac30a9826624acc6905ea38df17409b60d5cc.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "8ed1e36229e47ed0a5fe0fe6bfbee0cc5c6f724de04e9b15fab076b82b473fda", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a9cd3a3f80cdb186105b11fc6f49ea6ce01d08c6960bbff2e75357f9cb4327a", "generation_seconds_batch": 22.739051164942794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.711745262145996, "target_z": 6.218749824596399, "ce": 6.09409761428833, "genuineness": 3.7040140628814697, "identity": 0.11150405555963516, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8ed1e36229e47ed0a5fe0fe6bfbee0cc5c6f724de04e9b15fab076b82b473fda.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "8ee4e3557f8a4daa0d9a828e2a68f72b78ac27fb08fdda3737ad67d65ceb09bc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78ab3a049a15b382a477e5446a96bd372af78e0de69e43cbd3a7f1a41c414ed9", "generation_seconds_batch": 21.555165598983876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8601595163345337, "target_z": 1.0546875505971927, "ce": 5.871703147888184, "genuineness": 4.21237325668335, "identity": 0.5541324019432068, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8ee4e3557f8a4daa0d9a828e2a68f72b78ac27fb08fdda3737ad67d65ceb09bc.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "8f2f04d61d20ddebac7f65e013534856a0c993be5e9a94d379772dfe12b02b03", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fd9ab47df5f90b0cc7c9d19243265cab78a7aad57d990c97b6556f69e5188eb8", "generation_seconds_batch": 23.28264883707743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 5.839932441711426, "genuineness": 4.068024158477783, "identity": 0.5000184774398804, "hypothesis": "La porte est encore ouverte. J'ai. 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_Astonishment_Surprise/8f2f04d61d20ddebac7f65e013534856a0c993be5e9a94d379772dfe12b02b03.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": "8f57aa902312bee6df0865168099cac868b3811b1f9accc32cac619128549289", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3226c303009824510cb445d68e6da16cd48c940f7fcd1e5e1f4aa2262b418011", "generation_seconds_batch": 21.90396879101172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.468440294265747, "target_z": 2.156250013492585, "ce": 5.895530700683594, "genuineness": 3.71028995513916, "identity": 0.2970995306968689, "hypothesis": "De weg gaat linksaf na de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8f57aa902312bee6df0865168099cac868b3811b1f9accc32cac619128549289.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": "8f8a2328e1a728fd50a21113934585ef129b20a06802f73cce7d7d55fc100224", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a4dde5623336d342742f886aa9f3bd32a858dd357621171a42baa6deb268045", "generation_seconds_batch": 16.34152144996915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348505973815918, "target_z": 3.749999730148306, "ce": 6.173524379730225, "genuineness": 3.8922953605651855, "identity": 0.6723032593727112, "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_Astonishment_Surprise/8f8a2328e1a728fd50a21113934585ef129b20a06802f73cce7d7d55fc100224.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "8fa49e31bcc8431ce6b46b10704939e553504fbef1fe8c9933934451af1fde10", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "022ba78200807356c8a0f2950466d9b7afb1328eebc6385d4d6f5b60ea949e13", "generation_seconds_batch": 21.98106492497027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1289283186197281, "target_z": -0.26953124494028075, "ce": 6.538887023925781, "genuineness": 4.394378662109375, "identity": 0.5172641277313232, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8fa49e31bcc8431ce6b46b10704939e553504fbef1fe8c9933934451af1fde10.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "8fe90d70c578f64cee7d401875f49d485f465b0765c6b254745b9fd392ec1b29", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8338ae02f038442490d3833e64006fa1e60e1e66040b59a8f40a7dbfd0b536e5", "generation_seconds_batch": 22.68692596803885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6919115781784058, "target_z": 0.7499999460296612, "ce": 5.935244083404541, "genuineness": 4.13078498840332, "identity": 0.5625175833702087, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/8fe90d70c578f64cee7d401875f49d485f465b0765c6b254745b9fd392ec1b29.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "904989868177485aaef488e6d619b52a5a3b4d1577e660d276fce4858113ea5a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7dbce8d3c63c45ab9dd3f186f2109529313e43ae680e178738e85dcece569bde", "generation_seconds_batch": 19.277489176020026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.314852714538574, "target_z": 5.499999622207628, "ce": 6.070269584655762, "genuineness": 4.118232727050781, "identity": 0.10148070752620697, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/904989868177485aaef488e6d619b52a5a3b4d1577e660d276fce4858113ea5a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "90afaf18efb8fb5369d6025f4d42af048005751cd3c8e57f701a874f66ec0749", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c554f170a58576cd2fb3c74dc9b573f799af1cb1f4af182e49ffb3d9b45087ba", "generation_seconds_batch": 23.181026563979685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 6.221180438995361, "genuineness": 4.425758361816406, "identity": 0.614013671875, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/90afaf18efb8fb5369d6025f4d42af048005751cd3c8e57f701a874f66ec0749.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": "90bbcc772e1c48ab1e4a593547e92d96fb0affc72d43b976ca07cc661f6fecba", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c34cb87129fea1d23b832a871c84e975cd9739c0e5750893844841ee6fe614c9", "generation_seconds_batch": 17.403101871022955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.210456609725952, "target_z": 3.500000053970339, "ce": 6.229123115539551, "genuineness": 4.300237655639648, "identity": 0.5233912467956543, "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_Astonishment_Surprise/90bbcc772e1c48ab1e4a593547e92d96fb0affc72d43b976ca07cc661f6fecba.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "90e9d9023bd4f3304363e0e3d6a94be51549f01ab4986ecf7a8482dc127481ac", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0637c2a11177d6d6e9d01e0e5b8d1c7b770860c0ec0317534131920b913977b2", "generation_seconds_batch": 14.980477550067008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6763737201690674, "target_z": 4.343749878566737, "ce": 6.046441555023193, "genuineness": 4.15588903427124, "identity": 0.5707834959030151, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/90e9d9023bd4f3304363e0e3d6a94be51549f01ab4986ecf7a8482dc127481ac.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "912f0d47b1aa1bc33fa672dcdfb8238334211625a75e39bbf6e1ee822d365c93", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "73beb56f437ecb72855fd07c9cf66c7bda5b3ea8dba0ce731746bd171bb71124", "generation_seconds_batch": 21.00783088908065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.573695659637451, "target_z": 5.968749716655721, "ce": 5.764476776123047, "genuineness": 3.9173994064331055, "identity": 0.03567444533109665, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/912f0d47b1aa1bc33fa672dcdfb8238334211625a75e39bbf6e1ee822d365c93.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "91935ac2f0a17dbddb55c3d0ec27f63f25436958318e48a8a05edc9525893b9f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8f91c22ac80c76cde908baf43549daaba1469e2ed733544bfdd1c9cbd88453b0", "generation_seconds_batch": 21.555222240043804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7997628450393677, "target_z": 0.945312557343485, "ce": 5.760505676269531, "genuineness": 4.068024158477783, "identity": 0.3640161156654358, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/91935ac2f0a17dbddb55c3d0ec27f63f25436958318e48a8a05edc9525893b9f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "924b8fa1579f97db5cce002265a3b8315812a8db170063229dae477410d1f1ac", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1f55e87db54362d20cf855d4c74b366eae23b8f3eb423da51857ac54b6b82cd3", "generation_seconds_batch": 23.524087914964184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17152953147888184, "target_z": -0.19238283147394722, "ce": 6.0305562019348145, "genuineness": 4.444586753845215, "identity": 0.4588242471218109, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/924b8fa1579f97db5cce002265a3b8315812a8db170063229dae477410d1f1ac.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "924fafbaef8087e0ebaedc3951a81946c63176c06034be4f6be4a3e279d717b9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "28f4b56a32dbb1e0a89389e7a64160524f9892ae387459b4c10a96abf596311e", "generation_seconds_batch": 21.319962805020623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6237460374832153, "target_z": 2.437500026985169, "ce": 6.324435234069824, "genuineness": 4.218649387359619, "identity": 0.29511022567749023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/924fafbaef8087e0ebaedc3951a81946c63176c06034be4f6be4a3e279d717b9.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "927af2c4d02a5737636ade2b7c06c6d8c023ba4527232d0410c43371625852b0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ffce9b2418d7c3b1f08ee2fdc59c0ee019083a1418600a302627dc6c3b4729de", "generation_seconds_batch": 22.985311067081057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7630934119224548, "target_z": 0.8789062651791578, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.5030181407928467, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/927af2c4d02a5737636ade2b7c06c6d8c023ba4527232d0410c43371625852b0.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "92b03f0aa114fda46622134c9b351bd3139165b19e8fc1ed000715fb6de59639", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f038d482e7edcf1f0ff84b74baea94786e449a1d08b62cecc6edee418def629c", "generation_seconds_batch": 23.461217516916804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.088804006576538, "target_z": 1.4687499325370765, "ce": 6.149696350097656, "genuineness": 4.20609712600708, "identity": 0.4228256642818451, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/92b03f0aa114fda46622134c9b351bd3139165b19e8fc1ed000715fb6de59639.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "931d8a75de9beae03a756beafb29c50d8317388d945b4da6c6f13b40f01c0221", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ae886765dea360dc50727546c3924fdd54c2be9bd45497bd7bb01ca3d91deee7", "generation_seconds_batch": 17.121350971981883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09441593289375305, "target_z": -0.33203124494028075, "ce": 6.1894097328186035, "genuineness": 3.9801597595214844, "identity": 0.4768896698951721, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/931d8a75de9beae03a756beafb29c50d8317388d945b4da6c6f13b40f01c0221.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "932e07b08c7926c330f7d5bac9334b32eaf20c0affc6351a9941f0bf39ffcf49", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d104546e03be16b8c3ecd1ea9cdc47c9cdab61f55644659a7528714ccfc3a41c", "generation_seconds_batch": 17.90488596400246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9291843175888062, "target_z": 1.1796876045675313, "ce": 6.165581703186035, "genuineness": 4.6203155517578125, "identity": 0.6646679639816284, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/932e07b08c7926c330f7d5bac9334b32eaf20c0affc6351a9941f0bf39ffcf49.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "933f311c5447e0bbc68549943b8dd269c95b872cf8b688a661df57a67392418b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b00b04b874c70673cc6cadb12976a2340954fadf68bec1598f9cfe6f0d50a77b", "generation_seconds_batch": 24.215149392955936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.503811836242676, "target_z": 4.0312499595222455, "ce": 6.141753673553467, "genuineness": 4.030367851257324, "identity": 0.6871270537376404, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/933f311c5447e0bbc68549943b8dd269c95b872cf8b688a661df57a67392418b.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "93bc3d4fc8d476e26aec255cf3611fb807b6b010ac0eab228fce8cf89f465711", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2db7d9bb7989cf34981b730ca9cd913865e2a269e0c9b0aad10ebbb603d1fcb6", "generation_seconds_batch": 21.548883691080846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7799108028411865, "target_z": 4.531249743640891, "ce": 5.95112943649292, "genuineness": 3.8295347690582275, "identity": 0.7280086278915405, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/93bc3d4fc8d476e26aec255cf3611fb807b6b010ac0eab228fce8cf89f465711.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "9477a7ce1f96f944e5edf62515b89a0a2367fe5cae3b32117ad865bd79a6720d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bf12e8c6eb14c06f91fdfde60e059f489c77262f09e8c9c56b26fdad673ef583", "generation_seconds_batch": 21.167305591981858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7617956399917603, "target_z": 2.687500134925847, "ce": 6.117925643920898, "genuineness": 4.162164688110352, "identity": 0.6196198463439941, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9477a7ce1f96f944e5edf62515b89a0a2367fe5cae3b32117ad865bd79a6720d.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "95108e535f6ffccaefa98314d42773208bc97ab781ab595a4e1d36f0326ef820", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "caaf65241e8d26269102cc0908e2003096dd9aa42789dc7129485d32b30055f8", "generation_seconds_batch": 22.480133482953534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44169682264328003, "target_z": 0.296875020238877, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.614154040813446, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/95108e535f6ffccaefa98314d42773208bc97ab781ab595a4e1d36f0326ef820.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "9615710c5b7fbb9ae8f59617b71e0b0618fb60c43d9e55a6feec27fcfb91e9a3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0654c28e94f6b5f98f45e8b76de75b66655a0c6c0e799f8e8e47c7708e64240c", "generation_seconds_batch": 15.919007880031131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3571341037750244, "target_z": 3.7656247908649374, "ce": 5.863759994506836, "genuineness": 3.961331605911255, "identity": 0.43511274456977844, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9615710c5b7fbb9ae8f59617b71e0b0618fb60c43d9e55a6feec27fcfb91e9a3.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "9626e36caf3f33ce5271d2bb2bc44a99134753ee73307650d19cb437ecd9351f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dd5dcf5dfc56cfdeabab36684d62bc09db979316ad4b14abe18def4489ce3da7", "generation_seconds_batch": 19.932472829008475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.194059371948242, "target_z": 5.281249635700213, "ce": 5.871703147888184, "genuineness": 3.835810661315918, "identity": 0.3844729959964752, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9626e36caf3f33ce5271d2bb2bc44a99134753ee73307650d19cb437ecd9351f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "963c18aa1dcfcd055d3b9fc42eb1ee67e4dec9855bf5832a02853d4931ad460a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9890c49d949f3d68adb39c97a149a6e67c451bfb05bf0a6e8cd7965221a1b55f", "generation_seconds_batch": 20.952991814003326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013527512550354004, "target_z": -0.4785156494553098, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.6324619054794312, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/963c18aa1dcfcd055d3b9fc42eb1ee67e4dec9855bf5832a02853d4931ad460a.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": "964d6a9d5c14aa8717b1da7e1b3763602b6d5769d6d5778d16031b6f51462246", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a72ff13b93acff791d97a972695467fc3b5d7a1cd12ebae50e1fcd14f8b0c3ca", "generation_seconds_batch": 21.347534024040215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6530851721763611, "target_z": 0.6796874966268538, "ce": 6.197352409362793, "genuineness": 3.8169827461242676, "identity": 0.5602472424507141, "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_Astonishment_Surprise/964d6a9d5c14aa8717b1da7e1b3763602b6d5769d6d5778d16031b6f51462246.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "964e3b3db7c65fa8053bad403a3c2d4383a616ee078218366e3d27beac915302", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7128cec43695caaca7ed6524936795ac670fe5d80eb4d23121a7114034b929a6", "generation_seconds_batch": 17.190116959041916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3692171573638916, "target_z": 1.9765624628953922, "ce": 6.403861999511719, "genuineness": 4.300237655639648, "identity": 0.556887686252594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/964e3b3db7c65fa8053bad403a3c2d4383a616ee078218366e3d27beac915302.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": "9695f52f5abce26877bbac378685eb049d9130263f462e2ee45860be607b2a99", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0c7ec319ae6af11b098a2955dab34546135f216fae677e870bec109536bf1d16", "generation_seconds_batch": 15.51466859295033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.624605178833008, "target_z": 4.249999946029662, "ce": 6.205295085906982, "genuineness": 4.168440818786621, "identity": 0.48785969614982605, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9695f52f5abce26877bbac378685eb049d9130263f462e2ee45860be607b2a99.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "96ddc28249f453957aa30b070d1ab6550ae4828ad69253232fc789afdd5d2b5d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d4536e72b5db01c2b5067b1291d59ab0e61a160a927ee86f283bb173dc3430cc", "generation_seconds_batch": 22.62009094201494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6151179075241089, "target_z": 2.4218749662685384, "ce": 6.435632705688477, "genuineness": 4.394378662109375, "identity": 0.4056450128555298, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/96ddc28249f453957aa30b070d1ab6550ae4828ad69253232fc789afdd5d2b5d.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": "973ee4043cd21b7a08c453a02bd914c3f2e7179bf704ae946e62c35d124c71d5", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f61cd0cb9177d3a79d5f552bcfed593d088baab03aaaa19204289d58067a06f9", "generation_seconds_batch": 23.227680545067415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8144233226776123, "target_z": 4.593749986507415, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.5803073644638062, "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_Astonishment_Surprise/973ee4043cd21b7a08c453a02bd914c3f2e7179bf704ae946e62c35d124c71d5.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "975474187c4335258a7e7d69000fe8dfb0e2b738bf68325b2a10542527143be0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "30ef2106ca7966127aba6c655604c598ea21c0f54156c0fd9e6ddf877beaccb5", "generation_seconds_batch": 22.710137857007794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0206384658813477, "target_z": 3.156250013492585, "ce": 6.23706579208374, "genuineness": 4.137060642242432, "identity": 0.3333623707294464, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/975474187c4335258a7e7d69000fe8dfb0e2b738bf68325b2a10542527143be0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "97f0eeee6d8a5b7dc9496a123173b37e1faf36b022d7c52fc41f5a7d269b541b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c9a5baac32dec6a278e272190a3fe3fa6df5f5398a798d3da5e58737e480542b", "generation_seconds_batch": 19.618143899017014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3131345510482788, "target_z": 1.875, "ce": 6.062326908111572, "genuineness": 4.2751336097717285, "identity": 0.5687943696975708, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/97f0eeee6d8a5b7dc9496a123173b37e1faf36b022d7c52fc41f5a7d269b541b.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": "98e27bf6e7fd8234b51f4755bd83a25a20bc01d31635780cf021456a589f15da", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "176876ceec43ca9fae5dc77a276ad0df4ec7c2323a8b4b0ef293c4ce39b48dc6", "generation_seconds_batch": 14.43047717702575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5118001103401184, "target_z": 0.42382815282845593, "ce": 6.229123115539551, "genuineness": 3.9048471450805664, "identity": 0.231806218624115, "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_Astonishment_Surprise/98e27bf6e7fd8234b51f4755bd83a25a20bc01d31635780cf021456a589f15da.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "9915e551f6eb7e1cd45cfe8e7deca5a81575e109b2b7171870dfcc2d090d9c5d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eac8617062fcb6ba085a67bf0c8cb568542ecb50f2a90d8fc2291658446721a5", "generation_seconds_batch": 22.080137225915678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7285810112953186, "target_z": 0.8164062381939884, "ce": 6.23706579208374, "genuineness": 4.18099308013916, "identity": 0.37278056144714355, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9915e551f6eb7e1cd45cfe8e7deca5a81575e109b2b7171870dfcc2d090d9c5d.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "99854aecb7fbbf7dbfcd8a6d898508780cb344dac6f68b70f6c344625842ab1c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cb97b104368f7875bc142df90d99744f3d948d8142416234757bcdd44a5db13c", "generation_seconds_batch": 16.280514121055603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004807174205780029, "target_z": -0.5117187415671346, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.5709402561187744, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/99854aecb7fbbf7dbfcd8a6d898508780cb344dac6f68b70f6c344625842ab1c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "99b375e2fe64b02d78e6613dca140bad193cfa12eb230ffe0f6f4c97397efcca", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1bf0cb2d319f4e8d1188b5cffab9498a014e23bb6d68a46a7666f7bdb1c6853", "generation_seconds_batch": 23.277685089968145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9179604053497314, "target_z": 4.781249851581569, "ce": 6.197352409362793, "genuineness": 3.961331605911255, "identity": 0.4323910176753998, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/99b375e2fe64b02d78e6613dca140bad193cfa12eb230ffe0f6f4c97397efcca.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "e2cd74777b74e6cc82a0c77d647dd72de002d52c297cad8d9c12e567610c6a0c", "generation_seconds_batch": 16.798953515011817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06313908100128174, "target_z": -0.38867187415671345, "ce": 6.3641486167907715, "genuineness": 4.607763767242432, "identity": 0.34473633766174316, "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_Astonishment_Surprise/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "9a07c00a99731ca59a80573d557721bbd901e0908b44e39a8989b2d335b83178", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5621dbded09f2704f83afeb6b45afc9589e3dae604ef5af162cf4db8b1f2fd58", "generation_seconds_batch": 17.169835173990577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3821593523025513, "target_z": 2.000000053970339, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.4884418845176697, "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_Astonishment_Surprise/9a07c00a99731ca59a80573d557721bbd901e0908b44e39a8989b2d335b83178.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "9a28283db6e95dcbd9f1c51a43ddcd4f4d79ba30452b2f8f655c2d9d977e6ff7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a1b12b38df5f5463a2b7fcd6e731e4ec7374a63f4d6fd28971893283fe6afbac", "generation_seconds_batch": 21.872566436068155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.528836965560913, "target_z": 2.2656250067462924, "ce": 6.054384231567383, "genuineness": 4.243753433227539, "identity": 0.5137395858764648, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9a28283db6e95dcbd9f1c51a43ddcd4f4d79ba30452b2f8f655c2d9d977e6ff7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "9a79ae51edee637123a07ce18af4e5c24015707fd9a1e191657ac5beb0675f69", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7894bd62357f4aa5327f7f5ff52de8592daadc1c9407559339062549616ed0c7", "generation_seconds_batch": 21.35033815994393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09441593289375305, "target_z": -0.33203124494028075, "ce": 5.661221981048584, "genuineness": 4.099404335021973, "identity": 0.590752363204956, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9a79ae51edee637123a07ce18af4e5c24015707fd9a1e191657ac5beb0675f69.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "9a8eb2de1a1c2e00fbbf77291630c370658b31c30364f5e4cb89a34d0346c993", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1b1b383161da0c899a4f55c0fb29dbfd86aad08be55649be53ed273d4fb2a917", "generation_seconds_batch": 20.435606669052504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1595470905303955, "target_z": 5.218749824596399, "ce": 5.669164657592773, "genuineness": 4.074300289154053, "identity": 0.48159652948379517, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9a8eb2de1a1c2e00fbbf77291630c370658b31c30364f5e4cb89a34d0346c993.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "07f90cfe3b8d69f9d9ab55538aa0f57036e6d97630e959852206a89d604d891f", "generation_seconds_batch": 15.403886495972984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2092774659395218, "target_z": -0.12402343370521056, "ce": 6.149696350097656, "genuineness": 4.2751336097717285, "identity": 0.7555711269378662, "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_Astonishment_Surprise/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "9c2fa78caf02af66d5cea936d9a9ad8fada1fe9a00caea98ef13cf9a96d1a1fc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "14c140cd45784aa2e59edc3f0809f39b437c2e7dfc5292b7eb21b76c7a6ef158", "generation_seconds_batch": 16.659024941036478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1742258220911026, "target_z": -0.1875, "ce": 6.268836498260498, "genuineness": 3.9676074981689453, "identity": 0.5994792580604553, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9c2fa78caf02af66d5cea936d9a9ad8fada1fe9a00caea98ef13cf9a96d1a1fc.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "226e11c1477ed5417eff1fe02b07e28b5332e96909be451717c8e1f56ed5a881", "generation_seconds_batch": 13.882468300056644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13539938628673553, "target_z": -0.25781250337314615, "ce": 6.157639026641846, "genuineness": 3.9550557136535645, "identity": 0.6252161860466003, "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_Astonishment_Surprise/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "9cc56c782b49a4ddfd32229d2231df29edf3405dd4cd9ceb2a3ae9579cf14368", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a432b43885972bdd9507eec8008b7c756e5f4cabb67b7aab16f78e2268ca91d8", "generation_seconds_batch": 14.767227896954864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21790555119514465, "target_z": -0.10839845394408759, "ce": 5.903473377227783, "genuineness": 4.262581825256348, "identity": 0.4036352038383484, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9cc56c782b49a4ddfd32229d2231df29edf3405dd4cd9ceb2a3ae9579cf14368.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": "9cc94ec482dd49ae7ad9af0a1ab54502c4faa87339464d5dc4e5d78cface1d43", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "793877ca69c66db3e646a078066c2d42a9195d1d1f939a2b243fc09f60eba32e", "generation_seconds_batch": 14.749088245909661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4805232286453247, "target_z": 0.36718746964168447, "ce": 6.062326908111572, "genuineness": 4.243753433227539, "identity": 0.598426878452301, "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_Astonishment_Surprise/9cc94ec482dd49ae7ad9af0a1ab54502c4faa87339464d5dc4e5d78cface1d43.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "9ccd37ea1a952c4ec72700761e815bb005000e6edc573eb7e8c5a3382d92999c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7be3a7391f4d344f0dfaa6f47dd7f224458604ec8a88f79f98a01dc0b429ddc3", "generation_seconds_batch": 15.166599130025133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2095973491668701, "target_z": 1.687499919044492, "ce": 6.062326908111572, "genuineness": 4.15588903427124, "identity": 0.7297892570495605, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9ccd37ea1a952c4ec72700761e815bb005000e6edc573eb7e8c5a3382d92999c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "9d52073a128c341cfd7a47f51e0b9a89f04de6109d0e2f250d1e8a17e3ef09cc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "91fea41b1c32e5bcfd9424a19c371cbca02fbf40679ae322208a59fa2b425937", "generation_seconds_batch": 20.56345869798679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.029266595840454, "target_z": 3.1718750742092157, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.5327816605567932, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "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_Astonishment_Surprise/9d52073a128c341cfd7a47f51e0b9a89f04de6109d0e2f250d1e8a17e3ef09cc.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "9d60f8ea28d320aed278d22208e913b52b7a6fe63067860cb8bf5619c3088371", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8ff81d1257783f36477ba98d30107760a07868a86c7da5a45cc54233028d7f36", "generation_seconds_batch": 22.908519653021358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5719774961471558, "target_z": 2.343750094448093, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.4951528310775757, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9d60f8ea28d320aed278d22208e913b52b7a6fe63067860cb8bf5619c3088371.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": "9e8ca0266ece522331f10db12b2191c5cfa731d507e375daedd09615a43ba5eb", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1a939c5233c7d4ca8773de765bf12df906ab1b2b01e3e1078192c2810e495f3", "generation_seconds_batch": 17.080025703064166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0387537479400635, "target_z": 4.999999838088984, "ce": 5.879645347595215, "genuineness": 4.093128204345703, "identity": 0.3897220194339752, "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_Astonishment_Surprise/9e8ca0266ece522331f10db12b2191c5cfa731d507e375daedd09615a43ba5eb.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "9eeeb030d092f6a520c318f34826869d196a28df9ff810cf6cfdb05c4b3eb6f0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "da48fea524f1a426ae1a8dc83ea1c6b60253abcbc3aa21b56fbbdb462231d3d7", "generation_seconds_batch": 21.600641182041727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2578105032444, "target_z": -0.03613281798136253, "ce": 6.252951145172119, "genuineness": 3.9801597595214844, "identity": 0.4505757689476013, "hypothesis": "The 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_Astonishment_Surprise/9eeeb030d092f6a520c318f34826869d196a28df9ff810cf6cfdb05c4b3eb6f0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "9f51578c4d4e4dc7a48463b79ec851939d78f5e47abcd1b3bed12d922be30f9a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d4e6d14040223f0d2ce7acae081a17fe0146de11baf570129ce63a87e86d4232", "generation_seconds_batch": 15.773435486014932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14672376215457916, "target_z": -0.23730469213807598, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.5413473844528198, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9f51578c4d4e4dc7a48463b79ec851939d78f5e47abcd1b3bed12d922be30f9a.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "9fb1ce7eb863ad088b58f0df1c6a8dcc1ddcc01d23ba38c51543e96cd228bfce", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c15d2355decf4e711ecc460eab9a2bdf56c486f40d79e35e842b13ce22d152c", "generation_seconds_batch": 22.552628685021773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1621428728103638, "target_z": 1.6015625168657308, "ce": 6.332377910614014, "genuineness": 4.545003414154053, "identity": 0.551384687423706, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9fb1ce7eb863ad088b58f0df1c6a8dcc1ddcc01d23ba38c51543e96cd228bfce.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "9fd402dfcc71109cbcbb21ac758f620fd5e0edd2132cdb93f5ebdaac8f902c91", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ff6d74b480aad7186231658d8a7f06cc720767e1a524426e2e1a8c8846c9457b", "generation_seconds_batch": 20.920698574976996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2383972853422165, "target_z": -0.07128906966793562, "ce": 5.700935363769531, "genuineness": 4.005263805389404, "identity": 0.7062653303146362, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9fd402dfcc71109cbcbb21ac758f620fd5e0edd2132cdb93f5ebdaac8f902c91.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "9ff15d4146ce2c378fd81eaa8c44123314286b1ae3dd2296505e75801f0fd200", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5863d14aa611cd11ea9963264a0557ab8e1085a3feef19e4234745819c228f62", "generation_seconds_batch": 21.05020833807066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7436801791191101, "target_z": 0.8437499865074153, "ce": 5.998785495758057, "genuineness": 4.118232727050781, "identity": 0.5683687925338745, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/9ff15d4146ce2c378fd81eaa8c44123314286b1ae3dd2296505e75801f0fd200.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": "a0132f7091b93b1fc9caf2f27f089cd2dd4f479602557c6b7fe1a348df910a14", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0e3b906c9d017da4170c22bc659e2d0957dad9354a44ea3a981a69cb1dc91be", "generation_seconds_batch": 21.733972801011987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7695645093917847, "target_z": 0.8906250607166311, "ce": 6.23706579208374, "genuineness": 4.162164688110352, "identity": 0.5058693885803223, "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_Astonishment_Surprise/a0132f7091b93b1fc9caf2f27f089cd2dd4f479602557c6b7fe1a348df910a14.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "a04cfb240d0dd6b355deeef171b443933bf0f31089ec51723c94246a85c568b5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a806f70a2dada519e6629942a682f024b109e4fd34cd5fbbbe6d43aede3f066d", "generation_seconds_batch": 20.969679609988816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.581903338432312, "target_z": 0.5507811774773573, "ce": 5.80021858215332, "genuineness": 4.168440818786621, "identity": 0.5119870901107788, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a04cfb240d0dd6b355deeef171b443933bf0f31089ec51723c94246a85c568b5.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "a061ae55fcf8a07e992a2ffa2d26ccf645290112a697f1cd0d457ef962543417", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "575c41ab84970591047ee824c151c5e90de2a353763b0c9ec6c2ce59a0337089", "generation_seconds_batch": 17.22017014597077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1595470905303955, "target_z": 5.218749824596399, "ce": 6.038498878479004, "genuineness": 3.8169827461242676, "identity": 0.5056878328323364, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a061ae55fcf8a07e992a2ffa2d26ccf645290112a697f1cd0d457ef962543417.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "a07e6ac578a7094ac9c02f3b277bad1cf6a349b55cd7ed037ab2912b186f1531", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7d6b36529228623d1472e74194bb098bc8f1177d0cd567d71384e53bf033edae", "generation_seconds_batch": 22.890435353969224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7523082494735718, "target_z": 0.8593749392833689, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.492919921875, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a07e6ac578a7094ac9c02f3b277bad1cf6a349b55cd7ed037ab2912b186f1531.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "a0bb9c6836879ba9ba060043ece5a0a7d12dfb2ae989ef850ed8baa078215f2d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4a370bc75d22024851f24631a90ddd531424e9a9687ebd11d96e89d2d93d4f4d", "generation_seconds_batch": 21.38025987497531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5150356292724609, "target_z": 0.42968749662685385, "ce": 5.784333229064941, "genuineness": 4.532451152801514, "identity": 0.5175590515136719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a0bb9c6836879ba9ba060043ece5a0a7d12dfb2ae989ef850ed8baa078215f2d.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "a0c6f216a433ea35bbe99d14cb9f6e293793f4b46da831ccc08fc232dcc202bd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "37240bdb20f051a8167741777d77c7e7c059431e0e361cb62758cbb8f408c65e", "generation_seconds_batch": 21.506447579013184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28315553069114685, "target_z": 0.009765608977555679, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.5371038317680359, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a0c6f216a433ea35bbe99d14cb9f6e293793f4b46da831ccc08fc232dcc202bd.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "a12128e0221912ee36db24f6480f40b80ec2e3dde8569555725fafb10925396a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e5400158c24b73c04fe8b45d17ea2b31d74c67ecc0a74646060d34e741449d51", "generation_seconds_batch": 22.510940287960693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3230604827404022, "target_z": 0.08203124494028075, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.37420013546943665, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a12128e0221912ee36db24f6480f40b80ec2e3dde8569555725fafb10925396a.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "a133cc8b0f750935739100604e7682c894ae6e10772ab20a93522be3e4174b69", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f30f3f8da1073cf96c9be79b2c3eacb5181f4db57fffc167a0aaaf598b19266a", "generation_seconds_batch": 20.761532320058905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.452902317047119, "target_z": 5.749999730148306, "ce": 5.5738525390625, "genuineness": 3.7040140628814697, "identity": 0.600480318069458, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a133cc8b0f750935739100604e7682c894ae6e10772ab20a93522be3e4174b69.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": "a19891e21537313c8df061725e18484e1f70f8c434a7990f4fc0da3b72afee73", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d88e44187fdd92e35a9459de2ecc7ba4d918d6e0146f952c7174fe76d7a6515f", "generation_seconds_batch": 23.647055542096496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5115808248519897, "target_z": 2.2343751011943853, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.6572972536087036, "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_Astonishment_Surprise/a19891e21537313c8df061725e18484e1f70f8c434a7990f4fc0da3b72afee73.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "a1ba2b51598911e4dce96538db6f23be46987f95c028c471fa30ec1ab6a3f8a3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e527678d41c5a19e57a30a105ae966776651bb122156d1404362240f6be3912f", "generation_seconds_batch": 22.08045193599537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2225395441055298, "target_z": 1.7109375101194386, "ce": 5.982900142669678, "genuineness": 3.8671910762786865, "identity": 0.7245407104492188, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a1ba2b51598911e4dce96538db6f23be46987f95c028c471fa30ec1ab6a3f8a3.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "a283cfecf2edd5c33bca314a71621de5598ce2001a46a6450e56a3e09d7b9b7a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2250d570fc011a5a882107886f47f090b8e90759b1b0ed9337d0bf446eef1038", "generation_seconds_batch": 21.988814815995283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.573695659637451, "target_z": 5.968749716655721, "ce": 5.816103935241699, "genuineness": 3.540836811065674, "identity": 0.46673327684402466, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a283cfecf2edd5c33bca314a71621de5598ce2001a46a6450e56a3e09d7b9b7a.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "a287a1767c7bcdd08acd3e74122dec14862795a9a94c82925047fb6e4e9a4f5c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fd5424772dcad3ae09ed844dbaf2c021675614b27f7c97e548b33152d82fdaee", "generation_seconds_batch": 20.12719302298501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.314852714538574, "target_z": 5.499999622207628, "ce": 5.8875885009765625, "genuineness": 3.575355052947998, "identity": 0.4945414662361145, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a287a1767c7bcdd08acd3e74122dec14862795a9a94c82925047fb6e4e9a4f5c.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "a2ccc9fcadf1abbc1965933ccea48ffee11fa9f3c0de159493671ba67286954b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "58e8d40f198ba06ed22d6e7b048718dee0a305cc19b0db98a7f6970e01844784", "generation_seconds_batch": 21.689948641113006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6591174602508545, "target_z": 4.312499757133476, "ce": 5.8875885009765625, "genuineness": 3.722842216491699, "identity": 0.5669647455215454, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a2ccc9fcadf1abbc1965933ccea48ffee11fa9f3c0de159493671ba67286954b.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "a318824bfe8f96985ee37375df169c1ace66f3640da5a8187a1d23d257e40841", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9eadf73ee58854321d87f0f611b7c050774204ebc666925020438be437636596", "generation_seconds_batch": 20.372685540933162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1966552734375, "target_z": 1.6640625438509002, "ce": 6.324435234069824, "genuineness": 4.18099308013916, "identity": 0.4192328155040741, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a318824bfe8f96985ee37375df169c1ace66f3640da5a8187a1d23d257e40841.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "a34b5612dbac3544c1d960c2ffaf548921a6328a4b459d8d508d4a57d03e8ebd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "524d7e440a76d732b5342b63545eee215cd3cda9000113e858b60dfe2c8adbf2", "generation_seconds_batch": 23.26949869201053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.167215496301651, "target_z": -0.20019530786192402, "ce": 5.974957466125488, "genuineness": 4.055472373962402, "identity": 0.5460912585258484, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a34b5612dbac3544c1d960c2ffaf548921a6328a4b459d8d508d4a57d03e8ebd.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "a4550fecf744671047a09af361a9cbb02f73c44e2292a016c4ba27f5ec470b71", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6739c24fdc2c0081f97b8774d2ed1aef024eb049a13af6851bc99a9f8a8c1d94", "generation_seconds_batch": 21.872566436068155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2190847396850586, "target_z": 3.5156251146869697, "ce": 6.046441555023193, "genuineness": 3.9676074981689453, "identity": 0.43721774220466614, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a4550fecf744671047a09af361a9cbb02f73c44e2292a016c4ba27f5ec470b71.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "a49191d981f8f484a24f27b4e16b3e61dcd8ae33a4a3aea30de7eb807c664272", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9a001910ff6500a50c6730f0b4036c8d7680bb3e9f1b635b418e9c7ee1f2285f", "generation_seconds_batch": 20.137555740075186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.7410056591033936, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a49191d981f8f484a24f27b4e16b3e61dcd8ae33a4a3aea30de7eb807c664272.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "a666dc5f3e95320befc43b6bd9a4849b224ccd13ed7765ab4ed28d92322db2c7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ce664b1f2a6a868bc7b37122a9c7fefe83412926c7ce3dbe6029a215d7b222df", "generation_seconds_batch": 22.243952107033692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.589233636856079, "target_z": 2.375, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.35542958974838257, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a666dc5f3e95320befc43b6bd9a4849b224ccd13ed7765ab4ed28d92322db2c7.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": "a66ff7fb00c83a53b67c763b2f9b68fef06e9ecee562ef82dcc69485a331529d", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4d5e4187c442a24763819167c4fe4a670cfe87e93cb690b7ca6ce045f3608a3b", "generation_seconds_batch": 20.45118420489598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1586880683898926, "target_z": 3.406250121433262, "ce": 6.292664527893066, "genuineness": 4.375550270080566, "identity": 0.5719470381736755, "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_Astonishment_Surprise/a66ff7fb00c83a53b67c763b2f9b68fef06e9ecee562ef82dcc69485a331529d.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "a72a716efab9d106994bbb22148e76a40b063f508e231a298dde301974ae92d4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d2aa49e5fd4790004d9a5d1e081c4be43fe1bd94c571b63cd690561f84a07c94", "generation_seconds_batch": 22.62885622808244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728142261505127, "target_z": 4.437499811103814, "ce": 6.078212261199951, "genuineness": 4.049196243286133, "identity": 0.5930063128471375, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a72a716efab9d106994bbb22148e76a40b063f508e231a298dde301974ae92d4.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "a76207015cebe276323f45613c1c65bb6546e146d434d0d327c06dfa5577eed5", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "907e7ba08241f6ec6065aec6a2e3e34e12d5bd03e5d0d8ab44f91e0a52a646d7", "generation_seconds_batch": 16.69622411497403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3351937532424927, "target_z": 0.10400391911011979, "ce": 5.816103935241699, "genuineness": 4.243753433227539, "identity": 0.6797887086868286, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a76207015cebe276323f45613c1c65bb6546e146d434d0d327c06dfa5577eed5.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "a77f27da4fce6c6d6d563106d4c520279fcff70f25487c210691ed1ab6ae2e87", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a177f579b63476964fd3ff89342471e55542e257ddd2ba9b130c638db383b29f", "generation_seconds_batch": 21.134620998986065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6418612003326416, "target_z": 4.281249635700213, "ce": 5.847874641418457, "genuineness": 3.911123275756836, "identity": 0.5691099166870117, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a77f27da4fce6c6d6d563106d4c520279fcff70f25487c210691ed1ab6ae2e87.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "a7837cadf24088f19930f74f531b4471c4af35ae5b05243803943f7381fa0c94", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "55e51040a5aaf0228811a8228e6b199073c93bf2ec72c58ada649c6c83f2321e", "generation_seconds_batch": 21.766960295964964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2829362154006958, "target_z": 1.8203125033731462, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.44848576188087463, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a7837cadf24088f19930f74f531b4471c4af35ae5b05243803943f7381fa0c94.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "a7f526d166f6bf299cf37c88dfc1fdef08970e86896a1625baa87694a0743f85", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "92482f34208e2af1a7b4491114aa028f49c0da6d3e98fa8e690b38e15849c201", "generation_seconds_batch": 13.970532239996828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1650584638118744, "target_z": -0.20410157304108179, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.46173620223999023, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a7f526d166f6bf299cf37c88dfc1fdef08970e86896a1625baa87694a0743f85.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "313e784c9ef30803510e6d1ebce56367240518bb1151243c9b8a793a6b67dd2b", "generation_seconds_batch": 15.710826231050305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11706468462944031, "target_z": -0.29101562247014034, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.6387791633605957, "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_Astonishment_Surprise/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "d3341c96ce053ff226f5586a1614fa341e773bba6cac905e48350ef1df439f0f", "generation_seconds_batch": 16.213999754050747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04156884551048279, "target_z": -0.42773436403727494, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.7450858354568481, "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_Astonishment_Surprise/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.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": "a95173441d24ebfe49feb66fc5a3df5602a9bb58ac33d339b7b41f418a8edb5f", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3bdf8a3f79d4aff73553caa161e9685b2205fd7fd79648b1b38089c7e3f715c", "generation_seconds_batch": 16.02773202001117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9032999277114868, "target_z": 1.1328124224176381, "ce": 6.1894097328186035, "genuineness": 4.13078498840332, "identity": 0.3992496430873871, "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_Astonishment_Surprise/a95173441d24ebfe49feb66fc5a3df5602a9bb58ac33d339b7b41f418a8edb5f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "a977b05a9450ad57153c64320aab28475bb02a1bdfc721acabc797496ef6997d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9031ceb0060f94526c7d571f46d6a59f69cbce42c9d170b6de2aff469084991f", "generation_seconds_batch": 22.8259565429762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5301347970962524, "target_z": 0.45703124494028075, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.529729425907135, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/a977b05a9450ad57153c64320aab28475bb02a1bdfc721acabc797496ef6997d.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "aa18f1e256f554aa03e4441f4dc77abd13a31210a6080b8de4a1fabea07f1b94", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "87e49fec094ae70f470da700ecbb8f24cc9a725820ea3dcd8e24a0fc83def1e1", "generation_seconds_batch": 23.432178449002095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6293579339981079, "target_z": 0.6367187955374733, "ce": 6.443574905395508, "genuineness": 4.13078498840332, "identity": 0.3555440306663513, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/aa18f1e256f554aa03e4441f4dc77abd13a31210a6080b8de4a1fabea07f1b94.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "aa54b5bede079963381c03d2158ff76f3a20e8434a1b751c05f17206a23d1c74", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ce85053e70ed2bf8dff4fd94314fee05eb06d729f1929534fc9dc4f1bfec7d46", "generation_seconds_batch": 17.432979982928373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063778877258301, "target_z": 3.2343748853130303, "ce": 6.078212261199951, "genuineness": 4.494794845581055, "identity": 0.7311676740646362, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/aa54b5bede079963381c03d2158ff76f3a20e8434a1b751c05f17206a23d1c74.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "aaddb929d5de99134768711fbd34d897bd4cf6e16c5eac828b8573949bd307bd", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "28a0443efc08027e50ec53155281f16b838fe708be8df28c489d0cab4c21efe3", "generation_seconds_batch": 22.662235931959003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6237460374832153, "target_z": 2.437500026985169, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.5322271585464478, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/aaddb929d5de99134768711fbd34d897bd4cf6e16c5eac828b8573949bd307bd.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "7970c4c08e9e9a195ba67ea8c29d151c9803fc06103df9a9d2bb4641a3e35187", "generation_seconds_batch": 16.42527331900783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24378985166549683, "target_z": -0.06152343370521056, "ce": 6.427689552307129, "genuineness": 4.281409740447998, "identity": 0.35334068536758423, "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_Astonishment_Surprise/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "ac63d68ab28be7f40cd34427c320bf1d4931939e90f5646eace75ea81e5b7e92", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5cf39d7d7aaa5f68209f78dd328a0b19c86ea51b06eef7d3b2fc3910c750a7d6", "generation_seconds_batch": 23.545835557975806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6418612003326416, "target_z": 4.281249635700213, "ce": 5.80021858215332, "genuineness": 3.973883628845215, "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/manual-comparison-v1/audio/emo_Astonishment_Surprise/ac63d68ab28be7f40cd34427c320bf1d4931939e90f5646eace75ea81e5b7e92.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "ad56b0e821ad375028d32c7e477e8fd9c0786016de286d9d603745d4fe4f586f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c9bc614b53c70d48cacc21ecf40148095276351c1342e2cb2df5d1fe0172539b", "generation_seconds_batch": 15.933126776013523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5374650955200195, "target_z": 2.2812500674629232, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.5458613038063049, "hypothesis": "De deur 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_Astonishment_Surprise/ad56b0e821ad375028d32c7e477e8fd9c0786016de286d9d603745d4fe4f586f.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "ad7c47a683b7f2ccbad57787b2b875abb3b24b66cef61d9784a4b8c9817785e4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a76b2d4edabc12d6d1b33dd6d26f7a27db1fb16619eae6af54c768e2574a2b8", "generation_seconds_batch": 22.387362741981633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9352166652679443, "target_z": 4.81249997301483, "ce": 6.046441555023193, "genuineness": 3.773050308227539, "identity": 0.37381500005722046, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ad7c47a683b7f2ccbad57787b2b875abb3b24b66cef61d9784a4b8c9817785e4.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "794353b0bc4bf40d425ed8d83e1ddd12f9cc6b5552375f8d8be3e538294e63cb", "generation_seconds_batch": 16.670139239984564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0629197359085083, "target_z": 1.4218749662685384, "ce": 6.229123115539551, "genuineness": 4.049196243286133, "identity": 0.5404331088066101, "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_Astonishment_Surprise/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "adf0586ea1fbd09a36da8172d7ea26bf00c65f22691030e79db8248f0c18a625", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3213484e350a0735452c5bd9aa2fbd43d183c5149e920323256972ffa0338e6f", "generation_seconds_batch": 21.754361297003925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.635828971862793, "target_z": 0.6484374831342692, "ce": 5.8875885009765625, "genuineness": 4.293961524963379, "identity": 0.6047643423080444, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/adf0586ea1fbd09a36da8172d7ea26bf00c65f22691030e79db8248f0c18a625.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "ae29f8420919c8c9ba8a9ee928a4c33d9321e218320365865229439f8a7fa25f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bafd657efc4a06b8646c73d245b001614703f194df5195a5953eb8c5d2f60ae0", "generation_seconds_batch": 14.980477550067008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.452043294906616, "target_z": 3.937500026985169, "ce": 6.23706579208374, "genuineness": 4.162164688110352, "identity": 0.5447089672088623, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ae29f8420919c8c9ba8a9ee928a4c33d9321e218320365865229439f8a7fa25f.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "94ef3d4efce5d1f668d1a5f3d8f22692a23034b6122e56c87c9374a5d2039196", "generation_seconds_batch": 16.912360265967436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07284568250179291, "target_z": -0.3710937618060116, "ce": 6.427689552307129, "genuineness": 4.419482707977295, "identity": 0.4145790934562683, "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_Astonishment_Surprise/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "af27b22e21d478e2371f65e5f499e6f91d17af0218d50a4c0379b1db32d023a6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "15474771bf3a5a36ecd71157346cd09c0dfdff58a7491fb8edd26ef8babf4682", "generation_seconds_batch": 16.824962325044908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4511841535568237, "target_z": 2.1250001079406777, "ce": 5.760505676269531, "genuineness": 4.055472373962402, "identity": 0.5211057662963867, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/af27b22e21d478e2371f65e5f499e6f91d17af0218d50a4c0379b1db32d023a6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "af9d03cd92ebffc22193a213bd839f88b8484362051d93590c5f82bd0b642d51", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "929612015b3d36d540cef3ba9e26c236640323c65b97e8a743f79dbeb710208a", "generation_seconds_batch": 23.259098600945435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.317448616027832, "target_z": 1.8828125303583156, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.47115880250930786, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/af9d03cd92ebffc22193a213bd839f88b8484362051d93590c5f82bd0b642d51.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": "afcfc3f685418c67f667470a232b88d54ca47fbc4184fe31611e23885b3fbd45", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f05e45a71458f005c0b3ca002cf327a60f8c08a52d9e8fe712dfcafca97b856", "generation_seconds_batch": 21.616024777991697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46929931640625, "target_z": 3.9687497166557213, "ce": 6.3641486167907715, "genuineness": 4.143336772918701, "identity": 0.31559649109840393, "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_Astonishment_Surprise/afcfc3f685418c67f667470a232b88d54ca47fbc4184fe31611e23885b3fbd45.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "b01b6c890a69ad862f3f8ed0ab3d3df7665e88c1eabfe4712e33749be9ad09e1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5da901c201c228f5f699d8834740345ae9639a51b61d59efad8510c1df962bc0", "generation_seconds_batch": 19.6890890810173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06637461483478546, "target_z": -0.38281250337314615, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.780043363571167, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b01b6c890a69ad862f3f8ed0ab3d3df7665e88c1eabfe4712e33749be9ad09e1.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "b0bfe893cb54b7bc2785696b3ff62c018673e5cff52cf6105d193a7a66e6ebfb", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5e358ddeb68adf27ed88355ed1a4e75b41be5a51c7447c6e4d2dba47516f1cce", "generation_seconds_batch": 15.564999714959413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1682940125465393, "target_z": -0.1982421752723451, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.6057401299476624, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b0bfe893cb54b7bc2785696b3ff62c018673e5cff52cf6105d193a7a66e6ebfb.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "b0d7e78cbd022753dccf13d3f385d7b1acad4f46888297c7bbfed4c38bc12981", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e54bf3fba8393d2ea92b07a3b9a4be453d5cc6c20795164089205f95a4b37468", "generation_seconds_batch": 15.90621436201036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5219271183013916, "target_z": 5.8749997841186445, "ce": 5.935244083404541, "genuineness": 3.5220088958740234, "identity": 0.24982169270515442, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b0d7e78cbd022753dccf13d3f385d7b1acad4f46888297c7bbfed4c38bc12981.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "b13cb5a101467d9c64d5fb0976b8c1508592aafafe8244cd73ee1225ccca0200", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6682a6f1b42791db20f465712c5a7936c59c82025a634d00b73ceefd9b1eb8a9", "generation_seconds_batch": 21.283241955097765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.210456609725952, "target_z": 3.500000053970339, "ce": 5.839932441711426, "genuineness": 4.168440818786621, "identity": 0.4807612895965576, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b13cb5a101467d9c64d5fb0976b8c1508592aafafe8244cd73ee1225ccca0200.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "b177e93ab792c41b0004796b899e6394f7dbe0a75c5b2236842d1437cf1ab91c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "18892f9a549827f56cfd8886cdf08ad0e9eff0372fcb6309509f8d605aff0b04", "generation_seconds_batch": 23.121724072028883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7626547813415527, "target_z": 4.500000053970338, "ce": 5.831989288330078, "genuineness": 3.873466968536377, "identity": 0.37780386209487915, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b177e93ab792c41b0004796b899e6394f7dbe0a75c5b2236842d1437cf1ab91c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "b1c426143ede89862271e4733561f7a9eb924cb484138167534acb645b5e1b79", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "302b3b64fe883cce320ad87b6a1759179fc0b02969ca006aead1d42cf109eb97", "generation_seconds_batch": 19.6890890810173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269674152135849, "target_z": -0.014648413466333518, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.7837231159210205, "hypothesis": "Je trouvai 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_Astonishment_Surprise/b1c426143ede89862271e4733561f7a9eb924cb484138167534acb645b5e1b79.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "b265f550d037a2f0649546a3051a5446a8e8d84713b97599641adcd150786be7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "25198ea44820e9af3f1aee19f81a91a83ce803768cbd28f82db27f89cf38b9f9", "generation_seconds_batch": 15.706191648030654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.08966326713562, "target_z": 3.2812500674629232, "ce": 6.213237762451172, "genuineness": 4.494794845581055, "identity": 0.660661518573761, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b265f550d037a2f0649546a3051a5446a8e8d84713b97599641adcd150786be7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "b339bbff137ebe66a0a890a39adc5196d70658a37edbcb9b2ebd35ed3eca555d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc21bfeb1886585f6d7d4b26c55893a990baed3d5abe6f63f8a1ff624c36d3fc", "generation_seconds_batch": 21.257258409052156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25727126002311707, "target_z": -0.037109357290982595, "ce": 6.229123115539551, "genuineness": 4.394378662109375, "identity": 0.7729722261428833, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b339bbff137ebe66a0a890a39adc5196d70658a37edbcb9b2ebd35ed3eca555d.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "b3997ad3d093b607c4e9f20ffa4b32ceeb3aac9b76d65b3c32f1647bc58b1a3c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d685ee1a59d419574224dbae980d9d7f6d00a5e4d773614a05637fe624996bd6", "generation_seconds_batch": 22.914798087906092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.349365234375, "target_z": 5.5624998650741535, "ce": 5.974957466125488, "genuineness": 4.118232727050781, "identity": 0.5830246210098267, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b3997ad3d093b607c4e9f20ffa4b32ceeb3aac9b76d65b3c32f1647bc58b1a3c.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "b3a371c062a049e3bbedb6c02858256b82cd06c66458ed2c63d43101766bf5c0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "14b20799ef008fe7458f4f800989877991650865c848e66aae06335c27efc9a1", "generation_seconds_batch": 21.05092143593356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9162421226501465, "target_z": 1.1562500134925846, "ce": 6.133810997009277, "genuineness": 4.137060642242432, "identity": 0.5517334938049316, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b3a371c062a049e3bbedb6c02858256b82cd06c66458ed2c63d43101766bf5c0.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": "b3c0c28c554c17338919508cc22ebbbc5a5b05f42506bac6b166e14060425b43", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bfef65509de9adeff7a9749a886bd117b40826cf05438b5937d5b656c57f50e", "generation_seconds_batch": 20.186365406028926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2018284797668457, "target_z": 3.4843749932537076, "ce": 5.9431867599487305, "genuineness": 4.137060642242432, "identity": 0.4309081733226776, "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_Astonishment_Surprise/b3c0c28c554c17338919508cc22ebbbc5a5b05f42506bac6b166e14060425b43.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": "b3ebfc594010fc3749df148ef5d578c8da54d3b9ad0af070e895a3b4c19fef3e", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d21a25b06159b5a1a20142cce091637bd689b46ee41913439580d60e4cba3ed", "generation_seconds_batch": 23.09230534301605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8144233226776123, "target_z": 4.593749986507415, "ce": 6.316492557525635, "genuineness": 4.319066047668457, "identity": 0.5773749351501465, "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_Astonishment_Surprise/b3ebfc594010fc3749df148ef5d578c8da54d3b9ad0af070e895a3b4c19fef3e.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "b422680d7481831acff880f78dc2d958f0398909482b67bd138a3fa36af122ab", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "979db5e4761036818bcb88deb0813c28405bc0af544ff95d44d4e8aeaf1707ca", "generation_seconds_batch": 22.14605030894745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6763737201690674, "target_z": 4.343749878566737, "ce": 6.006728172302246, "genuineness": 3.973883628845215, "identity": 0.6103020906448364, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b422680d7481831acff880f78dc2d958f0398909482b67bd138a3fa36af122ab.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "924d8655e6d95bb084687bd4f5572d829b89ffc2adb55f090aca9c505442c3c7", "generation_seconds_batch": 16.508034121943638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05451098084449768, "target_z": -0.4042968809030058, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.5415688157081604, "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_Astonishment_Surprise/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "b48a2b76e2194eadead3eaf9025bcaff487371cb6e1c0bd302339ee43f564c5b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c525c375f088ce3ca0bebb9fca480728a26307c4efe5d02f4bc45bab50e5cbf7", "generation_seconds_batch": 21.319962805020623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9550685882568359, "target_z": 1.2265625708360697, "ce": 6.395919322967529, "genuineness": 4.231201171875, "identity": 0.41236478090286255, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b48a2b76e2194eadead3eaf9025bcaff487371cb6e1c0bd302339ee43f564c5b.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "b49357e1752802f1659129bb422dd766bbfbd573aac528813c469046d516f5d3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f38206bd4924da458bfe88a0669d1adbe3472e8092d42411c509ddc7acc2d32b", "generation_seconds_batch": 22.095168721978553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.675514578819275, "target_z": 2.531249959522246, "ce": 5.847874641418457, "genuineness": 4.099404335021973, "identity": 0.544925332069397, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b49357e1752802f1659129bb422dd766bbfbd573aac528813c469046d516f5d3.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "b4ddddb83e86e308205df7e7824dac01d5ecd09831b6a9327fa39876e1cfc9b0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e753f52bf9ed799e4949b6b8110834f47fee5db838c30dd24083738ff467f5ca", "generation_seconds_batch": 16.206984099932015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0931180715560913, "target_z": 1.4765624628953922, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.49156612157821655, "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_Astonishment_Surprise/b4ddddb83e86e308205df7e7824dac01d5ecd09831b6a9327fa39876e1cfc9b0.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "b4de2a4bca31e69ea7b8ae72a6a11d8ebe2f947f4757840747360085e8791f40", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db09c23ec3e9de4125273bf25fefa8f8af3634e2c6046082835760cb68ba787a", "generation_seconds_batch": 17.08570898498874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0025230646133423, "target_z": 1.3124999730148306, "ce": 6.395919322967529, "genuineness": 4.268857479095459, "identity": 0.5520952343940735, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b4de2a4bca31e69ea7b8ae72a6a11d8ebe2f947f4757840747360085e8791f40.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "b503150723fa3697d9db207380dc6de0f052640b1eeeee00491e710e01628d01", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4331d5a2774e83066d5c5daafa4e04f3eb880411254c1bdcc69418b11b14a930", "generation_seconds_batch": 24.53559007192962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0982913970947266, "target_z": 3.2968751281795545, "ce": 5.728734970092773, "genuineness": 4.143336772918701, "identity": 0.30655190348625183, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b503150723fa3697d9db207380dc6de0f052640b1eeeee00491e710e01628d01.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "b52382f6490b6931c749a5b3792f2a4f573d01effcb3eff7f8b5658eb2c3974f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "747ddd313da1b42c8aca7e9440e38d428157016f4492134123e85a94fe21e4be", "generation_seconds_batch": 20.88876463996712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8739608526229858, "target_z": 2.8906250607166313, "ce": 6.23706579208374, "genuineness": 4.099404335021973, "identity": 0.6219263076782227, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b52382f6490b6931c749a5b3792f2a4f573d01effcb3eff7f8b5658eb2c3974f.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "b5717d89cd517d4d5931d9e9740535d96dc7444c90e7518a9e0935441fd74145", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bfe7df81704bee1727c125acd4188d57ff07ccaa8712ba84f609a01d6306959a", "generation_seconds_batch": 23.073460677987896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.986985206604004, "target_z": 4.906249905551907, "ce": 5.911416053771973, "genuineness": 3.8044304847717285, "identity": 0.27733004093170166, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b5717d89cd517d4d5931d9e9740535d96dc7444c90e7518a9e0935441fd74145.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "b5e0ce80157cbc792cd565118711ed81a22a9df84e2c0bf95e31ccf363d5c4ba", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f1e2fcf0452c6648eb72a14f50fcb5dd89385dc7b048448c1bdd55b50b967c7a", "generation_seconds_batch": 16.206984099932015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3131345510482788, "target_z": 1.875, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.5636627674102783, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b5e0ce80157cbc792cd565118711ed81a22a9df84e2c0bf95e31ccf363d5c4ba.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "b681685181f6c18aec95afe657322a5cfde0fe218d3384a44470a2827940dd0d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4691f08a46d7570cb9d042d14b3388d9e71e648e1d1a6801545f88f1537feadd", "generation_seconds_batch": 22.359797756071202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11167211830615997, "target_z": -0.3007812584328654, "ce": 6.173524379730225, "genuineness": 3.873466968536377, "identity": 0.3949357569217682, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b681685181f6c18aec95afe657322a5cfde0fe218d3384a44470a2827940dd0d.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "b70cb5dfc469ff8aebb74b2b2319e4e7a0529433b53896769c2b3b52dc183a50", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "13a491c3474c6b679ed152e1d20e5bbfaa45428f621f96f1fdd32f163d2019c8", "generation_seconds_batch": 21.694813712034374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6237460374832153, "target_z": 2.437500026985169, "ce": 6.141753673553467, "genuineness": 4.356721878051758, "identity": 0.4904494881629944, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b70cb5dfc469ff8aebb74b2b2319e4e7a0529433b53896769c2b3b52dc183a50.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "b7bb3736699ca028ca1729da0b37334b3d4476ef057365c53cd06b34325bd83c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "af11ef524eadf36143255e22d8c52e1b2d6aed19dbdeecf5cb10015dcbb1c50e", "generation_seconds_batch": 15.603134391014464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0387537479400635, "target_z": 4.999999838088984, "ce": 5.919358730316162, "genuineness": 4.105680465698242, "identity": 0.5299568176269531, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu prends peur, dis-moi, Cathy, dis-moi.", "wer": 0.3888888888888889, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b7bb3736699ca028ca1729da0b37334b3d4476ef057365c53cd06b34325bd83c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "b861ec8f2a658ed4aa69508de5b15dbdb05d9e7dfde124cabd9da8bcb3a0347a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d0e3fc2aa282f34b583254682920ee90428e05e78c2fa2ea1ac71d9e2bc56e85", "generation_seconds_batch": 22.58347586391028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.08966326713562, "target_z": 3.2812500674629232, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.32066917419433594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b861ec8f2a658ed4aa69508de5b15dbdb05d9e7dfde124cabd9da8bcb3a0347a.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": "b883a69627274090406bdccb0efefdbf82409b3acc22175b51e6231869b735d1", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc9ecb536289e07247df53e52db4d9408c0c757c6a0612308e90c518f1618f91", "generation_seconds_batch": 14.749088245909661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0214974880218506, "target_z": 4.968749716655721, "ce": 5.967014789581299, "genuineness": 4.105680465698242, "identity": 0.4972578287124634, "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_Astonishment_Surprise/b883a69627274090406bdccb0efefdbf82409b3acc22175b51e6231869b735d1.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "b88f2d455e3f1d0bd637ad6f87c60d0a8d03a2295ebe91a6fed549cc542d6c6b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fbec63c981d9888a8efd61a6e49807b14ed7d145d1c6ae395ddba2dcbd1b0e61", "generation_seconds_batch": 22.781388895004056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6552422046661377, "target_z": 0.6835937618060116, "ce": 6.292664527893066, "genuineness": 4.256305694580078, "identity": 0.2905213236808777, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b88f2d455e3f1d0bd637ad6f87c60d0a8d03a2295ebe91a6fed549cc542d6c6b.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "b916f57afaf1121050df387fd884c6c03ce38ca5fbb0b43f2b6ba1f393fea41d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bfbd4f9547a31493c5a364fc303197b08dcc6c808c073cd2c2b402d1133b84f6", "generation_seconds_batch": 21.506447579013184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2777629792690277, "target_z": 0.0, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.47107958793640137, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b916f57afaf1121050df387fd884c6c03ce38ca5fbb0b43f2b6ba1f393fea41d.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": "b932bec0b17b72bf8fe502245662b897060144fec3051ab742cb614efcf75658", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4a1822e54e0d11c58208ff32d92757a8ec87813293efcf783e47a2c0d5c561f", "generation_seconds_batch": 23.227680545067415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2967374324798584, "target_z": 3.65624979761123, "ce": 6.0305562019348145, "genuineness": 4.319066047668457, "identity": 0.7507412433624268, "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_Astonishment_Surprise/b932bec0b17b72bf8fe502245662b897060144fec3051ab742cb614efcf75658.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "b939e642e747df99377973cea9d160004a9a20aa1986394a284e54a89baa4b4c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bee26b9918385418c9609f2ff3a3afad1bcd52e39abb78db8d2dbf9b55594d23", "generation_seconds_batch": 23.56130184594076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7674074172973633, "target_z": 0.8867186875967958, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.6863369345664978, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b939e642e747df99377973cea9d160004a9a20aa1986394a284e54a89baa4b4c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "b95461937dc28e4976139c1adddc86ae5c6db1c987f35eb6484ebca65046805b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3f955cbbc8187b9f3b31042cb3d4239c21e1751479da1d691e2b56cdeaf4a3b4", "generation_seconds_batch": 23.849680697079748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 6.173524379730225, "genuineness": 4.300237655639648, "identity": 0.45785924792289734, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b95461937dc28e4976139c1adddc86ae5c6db1c987f35eb6484ebca65046805b.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "b9ea8434150e3504b713faf8a19cda8e1bd1dc9e370438bca056d9af82f7e080", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5b0ecc19fe62fe4b349afafb05151cc6fe78377442cea302a94c67b7f8080ae5", "generation_seconds_batch": 20.32065028010402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19795309007167816, "target_z": -0.14453124494028075, "ce": 6.133810997009277, "genuineness": 3.8671910762786865, "identity": 0.41302523016929626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/b9ea8434150e3504b713faf8a19cda8e1bd1dc9e370438bca056d9af82f7e080.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "ba0d0a1fe5f28a865f3dbf8194b5233b10fbed0f2408c3e150e15a710dffa216", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "75c31381e3bd3672625712afd9dbe53907a215b19e3bdbbb39c11bb4f74fff9d", "generation_seconds_batch": 16.564259089995176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23516175150871277, "target_z": -0.0771484404515029, "ce": 6.070269584655762, "genuineness": 4.337893962860107, "identity": 0.678808331489563, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ba0d0a1fe5f28a865f3dbf8194b5233b10fbed0f2408c3e150e15a710dffa216.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "131f5843e175552259a401125af8a7555f0a125dec52e53eaded30f25022b0f8", "generation_seconds_batch": 16.572140228003263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33222782611846924, "target_z": 0.09863279099619315, "ce": 6.086154937744141, "genuineness": 4.143336772918701, "identity": 0.7459422945976257, "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_Astonishment_Surprise/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "bb30177857d7f921445794cfd9aabc1d81d0843ae5471f0085fb5e88d3c9f966", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "15fcf0a237ccea4140969f524e0172afb32738027db81caa5024ba95b93eb7a7", "generation_seconds_batch": 15.928920018021017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5689612627029419, "target_z": 0.5273438022837657, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.5063960552215576, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bb30177857d7f921445794cfd9aabc1d81d0843ae5471f0085fb5e88d3c9f966.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "bbbfb6ddf0e31d951ce225ec8099ed78302d73457e9b8a10a15a0b9edf076a65", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3375ecbfad69b9fe14621d75748ea0348251c3eb33220572214cc11cdb849a66", "generation_seconds_batch": 20.38187185698189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2786221504211426, "target_z": 1.8124999730148306, "ce": 6.09409761428833, "genuineness": 4.168440818786621, "identity": 0.6183929443359375, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bbbfb6ddf0e31d951ce225ec8099ed78302d73457e9b8a10a15a0b9edf076a65.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "bbc491b6cf48142f7f74d610980337a7ccf3ac892e1f514594aeea2de5b217eb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ae85acd82c1ccf768d9b05bb52cc9cb6d24dce41f0997c0ccd356bb8d57c5fa1", "generation_seconds_batch": 20.353434497956187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8127049207687378, "target_z": 0.9687499325370765, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.776847243309021, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bbc491b6cf48142f7f74d610980337a7ccf3ac892e1f514594aeea2de5b217eb.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "bc07e83e24a89667e1482bdd1ed0aa54209f80ad50eb090e1eb1c18e51a9bfe6", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "60179100fa3323aa8a105c616b3f6b341ae3fb23d0f629851604dffcf2b284dd", "generation_seconds_batch": 15.807827395037748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8148620128631592, "target_z": 0.9726563056569119, "ce": 5.959072113037109, "genuineness": 4.2374773025512695, "identity": 0.6020128726959229, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bc07e83e24a89667e1482bdd1ed0aa54209f80ad50eb090e1eb1c18e51a9bfe6.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "bc0ef1f6168e47d05c10f914440b91a7084282f6f8c25052ee790d11b4c69c29", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "69e648768a14ac48ba3d3dd45b007b361003c703fdec851afb9636dbfe3687c7", "generation_seconds_batch": 22.702861806959845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2804592549800873, "target_z": 0.0048828044887778395, "ce": 6.260893821716309, "genuineness": 4.419482707977295, "identity": 0.31173473596572876, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bc0ef1f6168e47d05c10f914440b91a7084282f6f8c25052ee790d11b4c69c29.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "bc3070d04df0fa912029bf5d9d75d0e6b3674cad50b92b1f1fce34ece22a5b3d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a8822874c2453f98435b553f17aaf27ed45598de92826ca4ce8c04a91cb1df88", "generation_seconds_batch": 22.210731366067193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 5.919358730316162, "genuineness": 4.118232727050781, "identity": 0.1958562433719635, "hypothesis": "Die Tür ist noch offen? Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bc3070d04df0fa912029bf5d9d75d0e6b3674cad50b92b1f1fce34ece22a5b3d.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "bc6305f1821d223302de6ad364fdac67918fca2f4202e18a9b65d317758e10e6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0a79cefb53bc9023a3bf3280f9269e504b3aeae10d65a5361bfcbe964de6c2fa", "generation_seconds_batch": 20.87781484099105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24594686925411224, "target_z": -0.05761719551122216, "ce": 6.395919322967529, "genuineness": 4.243753433227539, "identity": 0.5367884039878845, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bc6305f1821d223302de6ad364fdac67918fca2f4202e18a9b65d317758e10e6.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "bce210cac93b81d9d12c11558460ebb2cd5b35999ddd5b94a77a53e2c875024a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "94af92ef327403c1eefa5f33ca8f7a7c82cb9011dc452c9da113de8fbdc8315e", "generation_seconds_batch": 17.139711315976456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9179604053497314, "target_z": 4.781249851581569, "ce": 5.728734970092773, "genuineness": 3.8044304847717285, "identity": 0.4496125280857086, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bce210cac93b81d9d12c11558460ebb2cd5b35999ddd5b94a77a53e2c875024a.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "bcf98ddad7ce245138f48dccbea11bf9dacfe5848c314739116e5d978fb03beb", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d37d7f0f4587a56228b53d8d4517b26c9386e2989330dfd85fbb42c7d9c5e7f0", "generation_seconds_batch": 22.853345884010196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15373408794403076, "target_z": -0.22460938427615199, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.2990413308143616, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du 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_Astonishment_Surprise/bcf98ddad7ce245138f48dccbea11bf9dacfe5848c314739116e5d978fb03beb.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "bd725f868af427848ddc33761e798efbe534b4c0ac229d4edd57deb23780de9e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "187dd20c5e1009cc2d8f82c0810a41f7c26e3749e2e02d122f73107ca5eadc49", "generation_seconds_batch": 21.732644452014938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.606489896774292, "target_z": 2.406250121433262, "ce": 6.197352409362793, "genuineness": 4.3504462242126465, "identity": 0.4365993142127991, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bd725f868af427848ddc33761e798efbe534b4c0ac229d4edd57deb23780de9e.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "bd8eb4d91230d81459e86a80da7d0292079eecbb9689dbe42cc929c45adc0d30", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fc65a090cad440a739c71307965071695a59a9dab1fed5ccdf92735318a00b0", "generation_seconds_batch": 22.87108711397741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49993646144866943, "target_z": 0.4023437483134269, "ce": 6.078212261199951, "genuineness": 4.080576419830322, "identity": 0.5561954975128174, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bd8eb4d91230d81459e86a80da7d0292079eecbb9689dbe42cc929c45adc0d30.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "bda0c251e4560aabe5a88fa67e065533746c2c287e8b70e35964ae6fb3c6a240", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6eff826619bfc9fbb127b4f8016767266f3d507295ad7c7239620afba97b63d2", "generation_seconds_batch": 20.56345869798679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9343575239181519, "target_z": 3.000000053970339, "ce": 6.252951145172119, "genuineness": 4.319066047668457, "identity": 0.5334980487823486, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bda0c251e4560aabe5a88fa67e065533746c2c287e8b70e35964ae6fb3c6a240.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": "bdb7d5b3af886697ee3a8cc3a3c02da6c5a9a97cc6f99cc80d439fe7eb258fc9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56a7565b69b624e517da085d11b223f310897b82a4923c2fe3ddcc9e038099f8", "generation_seconds_batch": 23.14697915792931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5555803775787354, "target_z": 4.124999892059322, "ce": 6.086154937744141, "genuineness": 4.344170093536377, "identity": 0.6677907109260559, "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_Astonishment_Surprise/bdb7d5b3af886697ee3a8cc3a3c02da6c5a9a97cc6f99cc80d439fe7eb258fc9.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "bdf26c48169bfadb9347da38664b383ec5e1d000b9cdc9ec053cb097d8b9207f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "36778d50c3670ed62a313cacce567209d12ca75fa9b99161218cdbcb16d7c387", "generation_seconds_batch": 23.83226701593958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9507545232772827, "target_z": 1.218750040477754, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.4962279498577118, "hypothesis": "De deur 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_Astonishment_Surprise/bdf26c48169bfadb9347da38664b383ec5e1d000b9cdc9ec053cb097d8b9207f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "bf43d8b6e5966fb79982df415e7e75d2f3457f9df5afc57a5c95f3f3d4b157e0", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "37a8c9eeee1aabd789d4b405042467047cfe045a904ace57c1e19292b12bac38", "generation_seconds_batch": 16.69622411497403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5624901652336121, "target_z": 0.5156250067462923, "ce": 6.0146708488464355, "genuineness": 4.080576419830322, "identity": 0.7438506484031677, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bf43d8b6e5966fb79982df415e7e75d2f3457f9df5afc57a5c95f3f3d4b157e0.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "bf749bc97806e817309f222d9eb3e885feadc35edcc98193aee9683ca105326f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "44622f829be9255b07ca71416b151435a724a21f580edc81e2bcd8a8a4b14cfd", "generation_seconds_batch": 22.73095892299898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5204281806945801, "target_z": 0.43945310560440953, "ce": 6.0305562019348145, "genuineness": 4.419482707977295, "identity": 0.7423349618911743, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/bf749bc97806e817309f222d9eb3e885feadc35edcc98193aee9683ca105326f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "c04737caed56f853e119cf3b4247fb30f0585438aa10e7bb7e10a92ffe826fc9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1cbda33eab4f75b9818c6f245219f56eed383b2d3b9cccc2fcc3c8629ee8ebbf", "generation_seconds_batch": 17.410318601992913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12137873470783234, "target_z": -0.2832031190969942, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.5573629140853882, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c04737caed56f853e119cf3b4247fb30f0585438aa10e7bb7e10a92ffe826fc9.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c089dc8472dc866d007554a9e1294684d85dc734d3e24734ef45e027335801d8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4bc126edadcf3d08c389d390fc4614dd329aa14bd6e8f39c74e19c08a7ae4c99", "generation_seconds_batch": 17.803560441941954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2944799065589905, "target_z": 0.030273420212625864, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.6012395620346069, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c089dc8472dc866d007554a9e1294684d85dc734d3e24734ef45e027335801d8.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c0943c030cd5ceb976388a4efba3facb0ec5c1f1092e79baaf49cb549402130c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6db258f2b30c290e8a698a848f22424fb20d171616b55f6f401b990d4ba08982", "generation_seconds_batch": 23.072132674977183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3047257661819458, "target_z": 0.04882809885811716, "ce": 6.260893821716309, "genuineness": 4.362998008728027, "identity": 0.5258145332336426, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c0943c030cd5ceb976388a4efba3facb0ec5c1f1092e79baaf49cb549402130c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c0a4a9673fb6aa8aed60be9f16a9dcb0c55cfdb0dc7064915e742d65eb43e3b3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "fadd1c28bce813dee57e8ad00d4a42d50ce4f5f2f9cd60b6d2e5ee5d212a0403", "generation_seconds_batch": 23.344896973110735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9007041454315186, "target_z": 4.749999730148306, "ce": 6.006728172302246, "genuineness": 4.011539936065674, "identity": 0.5942791104316711, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "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_Astonishment_Surprise/c0a4a9673fb6aa8aed60be9f16a9dcb0c55cfdb0dc7064915e742d65eb43e3b3.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "c0d9944873b54349220b128e555fcc2b84bb0cd781ac4facab1e4908b20301e7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b80d723e2057cd06c5742bbb11b483bdae4e0877dd02fbd8971ebf26b9f2ad9c", "generation_seconds_batch": 19.48433412902523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8567047119140625, "target_z": 2.8593751551647237, "ce": 6.117925643920898, "genuineness": 4.21237325668335, "identity": 0.6562570929527283, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c0d9944873b54349220b128e555fcc2b84bb0cd781ac4facab1e4908b20301e7.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": "c1c1307992084e0357e8862b417b27ff7692890ae0ccbb262939bc95fa46acd0", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a70c8be7793c131fbf90ed3bb251533f3754a036c94520af59359db6ff463360", "generation_seconds_batch": 16.34152144996915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 6.213237762451172, "genuineness": 3.8546390533447266, "identity": 0.7065916061401367, "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_Astonishment_Surprise/c1c1307992084e0357e8862b417b27ff7692890ae0ccbb262939bc95fa46acd0.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": "c2f87564345e0b2bea129738d667e7b3071e94b6bf89742d5954e78755a292e1", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca20714c0ecf0bb9aa92b82afff6126190059f75d107700a860432c91dde092b", "generation_seconds_batch": 22.744390050997026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 6.157639026641846, "genuineness": 3.998987913131714, "identity": 0.6436948180198669, "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_Astonishment_Surprise/c2f87564345e0b2bea129738d667e7b3071e94b6bf89742d5954e78755a292e1.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": "c36a3502decfdd4a0d6e3f53bf6d1efbd8bcd4eed37cf9603a05e195c5b175d7", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "825ee7452da34a3105305a565e33342fdea109723acbe21d772af17e8fe59191", "generation_seconds_batch": 14.272608319995925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41365551948547363, "target_z": 0.246093788791181, "ce": 6.1894097328186035, "genuineness": 3.7793264389038086, "identity": 0.49381858110427856, "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_Astonishment_Surprise/c36a3502decfdd4a0d6e3f53bf6d1efbd8bcd4eed37cf9603a05e195c5b175d7.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "2aa17474480412d0c6e14f0a0c48f83eeb4e307d3831307c5a357019557e4d59", "generation_seconds_batch": 13.882468300056644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44169682264328003, "target_z": 0.296875020238877, "ce": 6.157639026641846, "genuineness": 4.362998008728027, "identity": 0.6484501957893372, "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_Astonishment_Surprise/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "c439c250d5f756d0fdb944ed2bcebb20a58c548d67b367696c23a6e2debf78ea", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4d6245f23c3b922c3ffa35d41b34b43e4b2a5d6f765f754eb963457cada7a3e0", "generation_seconds_batch": 20.796021185000427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5905314683914185, "target_z": 0.5664062381939884, "ce": 5.831989288330078, "genuineness": 4.2249250411987305, "identity": 0.5042438507080078, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c439c250d5f756d0fdb944ed2bcebb20a58c548d67b367696c23a6e2debf78ea.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c453776d4aad36c9aea541e8e8efc12b40484b40f3d6f3c42c2716d4d3ab312b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "912a9c8f5b6d05e86e5ef1418f5466bf87720eeda0a537b04365bd45e120da91", "generation_seconds_batch": 17.52603340893984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1759440898895264, "target_z": 3.437499811103814, "ce": 6.260893821716309, "genuineness": 4.231201171875, "identity": 0.6568591594696045, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c453776d4aad36c9aea541e8e8efc12b40484b40f3d6f3c42c2716d4d3ab312b.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "c47f97fd5b0124bf49f76d161213372fd545309560c8d6e7342fd1c1cb495542", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "07fea93243ef745b69d8089c744730944537f6ccb913d380267c735acac3e639", "generation_seconds_batch": 22.890435353969224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6164157390594482, "target_z": 0.6132812044625267, "ce": 6.38797664642334, "genuineness": 4.457139015197754, "identity": 0.6976277828216553, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c47f97fd5b0124bf49f76d161213372fd545309560c8d6e7342fd1c1cb495542.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "ec2fbf88998d95111072ed1b4f605b9e38c8b3d1e70201d38601140b6d246e32", "generation_seconds_batch": 15.403886495972984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5970025062561035, "target_z": 0.5781249257907842, "ce": 6.2767791748046875, "genuineness": 4.21237325668335, "identity": 0.5796310901641846, "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_Astonishment_Surprise/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c4df0593ac052d67e8a95baebaa47627870d5f3c3b8dc5ad49630ef8d82e8b2f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b70b8f665c1e11ca79bc6cced3aaf69302b9a3a94508c43d3445087eb12fd32", "generation_seconds_batch": 23.474562064977363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1586880683898926, "target_z": 3.406250121433262, "ce": 6.403861999511719, "genuineness": 4.494794845581055, "identity": 0.5562509298324585, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c4df0593ac052d67e8a95baebaa47627870d5f3c3b8dc5ad49630ef8d82e8b2f.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c51941212b588a846604e260ed1de49909dfbd4a14e7c0c4a232d5a507e30975", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "453b04321a943440634c167bde851da42900247d9127c5ce05c8a329a91b6589", "generation_seconds_batch": 23.56051128101535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4770684242248535, "target_z": 2.1718750742092157, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.41888299584388733, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c51941212b588a846604e260ed1de49909dfbd4a14e7c0c4a232d5a507e30975.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "c529791dce9a78779b19b6b2d4817138f0ffc2dd1b143f7807a9329d30400d66", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ff3487b67e5a351c69e471e6363eab4eaa4c0cd131173ff35a0df184586c861", "generation_seconds_batch": 20.086374146980233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7617956399917603, "target_z": 2.687500134925847, "ce": 5.903473377227783, "genuineness": 4.005263805389404, "identity": 0.41422003507614136, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c529791dce9a78779b19b6b2d4817138f0ffc2dd1b143f7807a9329d30400d66.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "c56d119959913eb7dc1be454759e398a3b3529eaeab67568218798a1a3963402", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cf454034d2321159914a71895d467de96b878c1ce6a68a04ddf57fb36bf49749", "generation_seconds_batch": 15.961635880055837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5115808248519897, "target_z": 2.2343751011943853, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.5307809114456177, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Ah !", "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_Astonishment_Surprise/c56d119959913eb7dc1be454759e398a3b3529eaeab67568218798a1a3963402.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c57ea884f21ba0985761b3349b8a113aa3a0180a09b4c653efc642e77f0f6400", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b23bfac0415d6984e62c48b7b6969960520e1e6a23735c3095d2198939fa8987", "generation_seconds_batch": 23.249038784997538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9360756874084473, "target_z": 6.624999676177968, "ce": 5.935244083404541, "genuineness": 3.936227321624756, "identity": 0.5274562835693359, "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_Astonishment_Surprise/c57ea884f21ba0985761b3349b8a113aa3a0180a09b4c653efc642e77f0f6400.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": "c58dbd4f46550fa2ddc981fe2624bc06360e8079e32a664bd9c6b2c8f459cc7f", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e37228e08383d46434b710faa0710f44f328a41976bc3510e537da8569ea5a44", "generation_seconds_batch": 24.276902699028142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9352166652679443, "target_z": 4.81249997301483, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.6127954125404358, "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_Astonishment_Surprise/c58dbd4f46550fa2ddc981fe2624bc06360e8079e32a664bd9c6b2c8f459cc7f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "c5a1ec46ee5aff9ca2e38687dac03ff2630329349132d639a7659f80d4124c7f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b3e9a675ad9fdb284ae0ad2c8c3c60cfad5a2ace3789bac8a379ebc6a8dd11d3", "generation_seconds_batch": 25.79019616707228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6496303081512451, "target_z": 2.4843749932537076, "ce": 6.1894097328186035, "genuineness": 4.375550270080566, "identity": 0.2838898003101349, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c5a1ec46ee5aff9ca2e38687dac03ff2630329349132d639a7659f80d4124c7f.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c5e3f13302de7758706f68019ead0321df69940c057d0985b312d7ec1f7da840", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37e335686b64d79d4a3919ef6675939d81eb9b80cb802482008c3ea79f759ad9", "generation_seconds_batch": 20.091293392004445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46929931640625, "target_z": 3.9687497166557213, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.5263214111328125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c5e3f13302de7758706f68019ead0321df69940c057d0985b312d7ec1f7da840.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "c697e77c87ef722dde0c2559b78d26bdd6b1fb014fd256b20751565f5f5596c9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4512c1789e11287ebe0342603d297762dfc17a5c3dacf2c2329b4ff2b4d3ab32", "generation_seconds_batch": 22.742209054064006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43091168999671936, "target_z": 0.2773437483134269, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.6355908513069153, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c697e77c87ef722dde0c2559b78d26bdd6b1fb014fd256b20751565f5f5596c9.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c6b6b035681eac1e436fe06a19d2f7917ae1805eda00a6a37f7ad721411e9aef", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ea95175d7d0ede614b32b8fc71862454c3754c10642459580e0757d822d26aca", "generation_seconds_batch": 22.425728995003738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26805636286735535, "target_z": -0.017578139335871233, "ce": 6.022613525390625, "genuineness": 4.18099308013916, "identity": 0.5185444355010986, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c6b6b035681eac1e436fe06a19d2f7917ae1805eda00a6a37f7ad721411e9aef.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "c7659e99897eb6aff6f61297e581e89ef396dfd3c2b3fc19cf68a964c17e75b2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6d9290987f4fad86adaa860d1451f809d9b2bb7969a69f3715a3ce858c1176e7", "generation_seconds_batch": 21.35033815994393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.7237667441368103, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c7659e99897eb6aff6f61297e581e89ef396dfd3c2b3fc19cf68a964c17e75b2.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "c791a2c93445c0a0b94fb822d8f802731af8f5b3c12439e1bd2f3493cd99b663", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "78ff64c8ac03ba8a483cd039ab5b71582a3ee7921421ce5945be04d2fa0cce60", "generation_seconds_batch": 16.534946339088492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0551507472991943, "target_z": 3.218749824596399, "ce": 6.268836498260498, "genuineness": 4.086852550506592, "identity": 0.5950875878334045, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c791a2c93445c0a0b94fb822d8f802731af8f5b3c12439e1bd2f3493cd99b663.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "3936368e77ec86854befd693ecc72f6218c523308ecfaa91561f760597e1ab29", "generation_seconds_batch": 16.670139239984564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5806056261062622, "target_z": 2.3593751551647237, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.6276441812515259, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Wanneer we kunnen praten.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c85e2205f68fbac4fc5f5ef9d7d6cd0df74b20132e36de17ae52e3926e422fbc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cffdfcc899271080e31924ccf6444d8906302ca501684f94e364c38c5d70a315", "generation_seconds_batch": 22.20311053597834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.607348918914795, "target_z": 4.218749824596399, "ce": 5.617537498474121, "genuineness": 3.8922953605651855, "identity": 0.41969507932662964, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c85e2205f68fbac4fc5f5ef9d7d6cd0df74b20132e36de17ae52e3926e422fbc.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "4657b7708c94004747903b2e2af9d63d6c00661e570d9a4d273f9332b24f6f3f", "generation_seconds_batch": 16.425562530057505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5387629270553589, "target_z": 0.47265630565691186, "ce": 6.348263263702393, "genuineness": 4.168440818786621, "identity": 0.2535753846168518, "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_Astonishment_Surprise/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "c896419d392c82421794ba40dbbaf4476a92a812150ff46a4acade226dd34ccf", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "006f491366e71a06c1fc4bc1be7c94cab8533d8d4b968a888b80ecc657e23680", "generation_seconds_batch": 20.207054694066755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.952472686767578, "target_z": 4.843749662685383, "ce": 5.816103935241699, "genuineness": 4.042920112609863, "identity": 0.7260774374008179, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c896419d392c82421794ba40dbbaf4476a92a812150ff46a4acade226dd34ccf.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "c8a13903527618cc1f29968a61969a59ddd51a8139f4530a3bc6776f507fc9d9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "49875f5856dd4f8bc13a74627688e0a7df2009a23d4e16b4f906051e0ee55eee", "generation_seconds_batch": 23.259098600945435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25996753573417664, "target_z": -0.03222655280220475, "ce": 5.959072113037109, "genuineness": 4.319066047668457, "identity": 0.6687965393066406, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c8a13903527618cc1f29968a61969a59ddd51a8139f4530a3bc6776f507fc9d9.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c904cb762824e0d05a699a4efeef965cdc674d288732e84d1c62d26bb104b453", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cdeac2eb030dd5b8e66a5319b1b5e6c14318a0bb90b4016dc59b8cf49adcb963", "generation_seconds_batch": 22.743080928106792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.377845287322998, "target_z": 1.9921875236120232, "ce": 6.205295085906982, "genuineness": 4.400654315948486, "identity": 0.4780874252319336, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c904cb762824e0d05a699a4efeef965cdc674d288732e84d1c62d26bb104b453.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "c95367103bab43931e70bf834a9db95d55db62f9e9f251fc929c84d50d7c60a4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f8b47aad59cf02abfa7acfc3720d42ee44862e38297c51fe278d883c22a4be0b", "generation_seconds_batch": 19.224119522958063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6427204608917236, "target_z": 6.093749770626061, "ce": 5.736677646636963, "genuineness": 3.8797430992126465, "identity": 0.5036941766738892, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c95367103bab43931e70bf834a9db95d55db62f9e9f251fc929c84d50d7c60a4.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "c96c8e6798f88578d41bcd0ae34e1cbe4ecdc11f42bb113e53d010a3d11952a5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "48b6e60e0cab8662807ee18e964e562834fef1f3485ddbb1e26186d5f423c505", "generation_seconds_batch": 21.766960295964964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0715478658676147, "target_z": 1.4375000269851694, "ce": 6.340320587158203, "genuineness": 4.394378662109375, "identity": 0.553591251373291, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/c96c8e6798f88578d41bcd0ae34e1cbe4ecdc11f42bb113e53d010a3d11952a5.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": "c9c023f5910efeebd56a73e9080e407d8c7baa2313c1272b33a0da21bf7bd29f", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "06b796e419979be96636ce14826b0de61552463c0c7285cd6eb293970164b7af", "generation_seconds_batch": 16.231904129963368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.074125289916992, "target_z": 6.8749997841186445, "ce": 6.038498878479004, "genuineness": 3.4937667846679688, "identity": 0.3108997941017151, "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_Astonishment_Surprise/c9c023f5910efeebd56a73e9080e407d8c7baa2313c1272b33a0da21bf7bd29f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "ca1dea3199e9356f27a9163627039d3ece1e5266b113dccf64b29aed538ffa50", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4e13bfb3f21c02439d2671810536d33afb68639a90d8885454f41a37d37b1351", "generation_seconds_batch": 16.433102365001105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22707290947437286, "target_z": -0.0917968809030058, "ce": 6.070269584655762, "genuineness": 4.519899368286133, "identity": 0.6413539052009583, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ca1dea3199e9356f27a9163627039d3ece1e5266b113dccf64b29aed538ffa50.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "ca944de27435d1587dd4c832583b9297a1b99434b1f892bf178f491b14d8a0aa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e4d2b9b184832ea7d7dbd5e4ea16ebdbfdba269b785e8cbbe8b23d43aca9572f", "generation_seconds_batch": 20.690998382982798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28800883889198303, "target_z": 0.018554678645491297, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.29592275619506836, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ca944de27435d1587dd4c832583b9297a1b99434b1f892bf178f491b14d8a0aa.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "cacd8248724307a0770259499f2ff22083914c964f59ccc2b1db47e71cb77b90", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3e8f0aa1c8b236107a18b212edafa0585e14d2846ec6128f1ec8eff73d8181d3", "generation_seconds_batch": 20.696922120987438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6418612003326416, "target_z": 4.281249635700213, "ce": 6.046441555023193, "genuineness": 4.13078498840332, "identity": 0.34414416551589966, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cacd8248724307a0770259499f2ff22083914c964f59ccc2b1db47e71cb77b90.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "cb102c3c4aeec2ca62f6ef09f68ed3410ce0ffa5e2a3001b55ffa2d914b1a6cc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3af02c7d209b5ca910c1b11c6a34c4483fa4e4fe0e0974987a8cea331d782bb2", "generation_seconds_batch": 20.989739108947106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03725479543209076, "target_z": -0.4355468674104211, "ce": 6.157639026641846, "genuineness": 3.9299514293670654, "identity": 0.3930133283138275, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cb102c3c4aeec2ca62f6ef09f68ed3410ce0ffa5e2a3001b55ffa2d914b1a6cc.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": "cbcd5afe925bdbf664b21948ea10b1402574c1086ba46f9fb906f8966ebd16a5", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fb841d100760bc80ea3bf2bc5b93108698584eec642f196a3edc9dc1262750e", "generation_seconds_batch": 23.041800025035627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2622251510620117, "target_z": 3.593749986507415, "ce": 6.1894097328186035, "genuineness": 4.137060642242432, "identity": 0.40458378195762634, "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_Astonishment_Surprise/cbcd5afe925bdbf664b21948ea10b1402574c1086ba46f9fb906f8966ebd16a5.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "cbffe243f3d5e90780c0356b9e29f460676ad7dd570deaac2dc463e470a91766", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1d9fd6451f2dbf4a4bc0d7fad2d7438b831edacd82f21451ca297cc6fa0c63f", "generation_seconds_batch": 24.53559007192962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.952472686767578, "target_z": 4.843749662685383, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.12878644466400146, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cbffe243f3d5e90780c0356b9e29f460676ad7dd570deaac2dc463e470a91766.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "cc9d24f24fc4fabf335d87a54de7fcf71084fa45358f9180f8dc347e48a6008d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a562317dc44957fd74e0049b3210e8e5875b32adc379b1753bebab0d038de930", "generation_seconds_batch": 22.913248167955317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3303908109664917, "target_z": 1.9062501214332621, "ce": 6.403861999511719, "genuineness": 4.381826400756836, "identity": 0.30791425704956055, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cc9d24f24fc4fabf335d87a54de7fcf71084fa45358f9180f8dc347e48a6008d.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cd58b0d1fe4d35af20336c33a12e4184a92f568eb4a0c1b26b958797b4bee51b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "48018e674c6277f81552afe85c8f18d83b0a00e541b38a672a0505c2293fda5b", "generation_seconds_batch": 15.748628080938943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 6.0146708488464355, "genuineness": 3.8671910762786865, "identity": 0.15905533730983734, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cd58b0d1fe4d35af20336c33a12e4184a92f568eb4a0c1b26b958797b4bee51b.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cd5c0c22c3032678419f6d671cdac3960364446d991d970aff7022ed9a37d0f4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "15424e4d03a4a809750e5310fc6e05ffc38b18bf9fd628347a24111beed98609", "generation_seconds_batch": 16.534946339088492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124175548553467, "target_z": 3.343749878566738, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.5999652743339539, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cd5c0c22c3032678419f6d671cdac3960364446d991d970aff7022ed9a37d0f4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "cd67e84145684e21e7f7bc4935a504247566350dac1255025e45bd5f5719032a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5744aa1f2717d026de3e0b5c28d5fef1169c1fae7a77cdaa05b0fe93b8e8f908", "generation_seconds_batch": 16.47373189695645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5219271183013916, "target_z": 5.8749997841186445, "ce": 5.919358730316162, "genuineness": 3.7542223930358887, "identity": 0.5438122749328613, "hypothesis": "Deur 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_Astonishment_Surprise/cd67e84145684e21e7f7bc4935a504247566350dac1255025e45bd5f5719032a.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cd6f07c3c0ef643716b31111bb2d48198e565fa2e8918912b043cc40c29eb4c7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "84a6a40280f31241b2d174b08a528c986c2f191c8ca7d0bcfd459fdf5b4d096a", "generation_seconds_batch": 19.277489176020026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5728366374969482, "target_z": 4.156250013492585, "ce": 6.181467056274414, "genuineness": 3.9927117824554443, "identity": 0.6901898384094238, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cd6f07c3c0ef643716b31111bb2d48198e565fa2e8918912b043cc40c29eb4c7.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "cd7bbf5b22f4583eab6d4d4e73e320c944716bb4cd2b8623daf7518800780f0e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89be9772c13c1607be15e6389e6b62907c1ec2dc0c4a828b8f0830b801932ffb", "generation_seconds_batch": 21.988814815995283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.952472686767578, "target_z": 4.843749662685383, "ce": 5.764476776123047, "genuineness": 3.578493118286133, "identity": 0.5228933095932007, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cd7bbf5b22f4583eab6d4d4e73e320c944716bb4cd2b8623daf7518800780f0e.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "cd9983f4b4f953e2c66aba6ad70d93c4404816a28796192ee18a4698551f9b8d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b095066eabb46a05e2113863c4f5bb383b2a4621052607198d036f102daca079", "generation_seconds_batch": 22.095168721978553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2182254791259766, "target_z": 1.703124979761123, "ce": 5.824047088623047, "genuineness": 4.042920112609863, "identity": 0.5274092555046082, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cd9983f4b4f953e2c66aba6ad70d93c4404816a28796192ee18a4698551f9b8d.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cda0381f4e6a459cc02161b96fb33007a1705dbd59b251ad97ce57f35eaad461", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c39cbeada98077e3cc087e9efd3d677b32c4a26ec7d461e0cbb734805de8dfab", "generation_seconds_batch": 22.062110222992487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.366621494293213, "target_z": 5.593749986507415, "ce": 6.117925643920898, "genuineness": 3.8922953605651855, "identity": 0.6053885221481323, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cda0381f4e6a459cc02161b96fb33007a1705dbd59b251ad97ce57f35eaad461.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "cdc4dbda4bdae78dab54947b85b5936d5511a9404bf231e2f44768471de9d29d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2449a76c7c8ec22d04d0cfb4d50808b29d2c8225b0785b619ca207b2b632dbe1", "generation_seconds_batch": 21.10992667300161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.727283239364624, "target_z": 2.6250001079406777, "ce": 5.704906940460205, "genuineness": 3.9173994064331055, "identity": 0.5261005163192749, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cdc4dbda4bdae78dab54947b85b5936d5511a9404bf231e2f44768471de9d29d.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "ce64deb12ecb8dff29546963623f1624325c4f0613788ebe540d3f911635e9b7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "92ff3bbf2140b6af74829d2ed161705f3a705c09144d1a7f1875b32393be0b59", "generation_seconds_batch": 23.123010474955663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0378947257995605, "target_z": 3.187500134925847, "ce": 6.173524379730225, "genuineness": 4.281409740447998, "identity": 0.3769237995147705, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ce64deb12ecb8dff29546963623f1624325c4f0613788ebe540d3f911635e9b7.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": "cecdc5c2d7d8381b76e8ec528e26fecd4a9f2a82141aab685f9a3f40e98394eb", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c95d66af866f5526690caf44edcebf38d36708b10cc1a67e81b06a363a8316bd", "generation_seconds_batch": 21.616024777991697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.848076581954956, "target_z": 2.843750094448093, "ce": 6.038498878479004, "genuineness": 3.9927117824554443, "identity": 0.6456531286239624, "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_Astonishment_Surprise/cecdc5c2d7d8381b76e8ec528e26fecd4a9f2a82141aab685f9a3f40e98394eb.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "cee5aa53c0a077943e392f14a09aafe752f86de3fe4934e57d4861bef50c9968", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "20d2da132a12bcfb1d9a79d84620c265ad9cdca67deb10753bb9c3ddf098cf0b", "generation_seconds_batch": 22.847708059009165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3131345510482788, "target_z": 1.875, "ce": 6.046441555023193, "genuineness": 4.545003414154053, "identity": 0.7273862361907959, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cee5aa53c0a077943e392f14a09aafe752f86de3fe4934e57d4861bef50c9968.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cee6aad65e1195280d2a38490ee223f49ff8a0dc8605bbac58565d36db9c2d11", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7ce5c1d627418a5b5f040a1b9030d34d7e1a6c57777f594fa2614c85a3adaa62", "generation_seconds_batch": 20.128429287928157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3408559262752533, "target_z": 0.1142577977424855, "ce": 6.1020402908325195, "genuineness": 4.300237655639648, "identity": 0.42919445037841797, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cee6aad65e1195280d2a38490ee223f49ff8a0dc8605bbac58565d36db9c2d11.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "cf1cc542200fa37ff781f9c4988c6125f70096a53152cb3c3193a2bef63fe7e0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a9688ed1891047f27f449a03db8f697593df4ad64a6f54b5fc7498f0a19ab747", "generation_seconds_batch": 22.927076056948863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.468440294265747, "target_z": 2.156250013492585, "ce": 6.006728172302246, "genuineness": 3.936227321624756, "identity": 0.28451862931251526, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cf1cc542200fa37ff781f9c4988c6125f70096a53152cb3c3193a2bef63fe7e0.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "3d2a3e068b123c84bc29ba93fc142a457c8201f761101b40a9f99191538ba41e", "generation_seconds_batch": 16.859611344058067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2815377712249756, "target_z": 0.0068359370783567285, "ce": 6.260893821716309, "genuineness": 4.2751336097717285, "identity": 0.5139429569244385, "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_Astonishment_Surprise/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "cf6b8492eaf3f4150cf01e1cbfbce35d5778da7333846ac04312179ad738f5a8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d1d9e4c6272bea84eddf93ad6bc5eb63128bbdbf49a77f07429b150c0afbfaf4", "generation_seconds_batch": 21.41557782597374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3139936923980713, "target_z": 3.687499919044492, "ce": 6.0305562019348145, "genuineness": 3.8922953605651855, "identity": 0.5108009576797485, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cf6b8492eaf3f4150cf01e1cbfbce35d5778da7333846ac04312179ad738f5a8.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "cf7489a5e28b9d37e569f69030201de759c79ead129f426df9a1630747c7f58a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "702d9d93d009b3701524bef4bf3df4644e682443badbc6c2aadcc51fa4e363d1", "generation_seconds_batch": 21.70191879302729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.666027307510376, "target_z": 0.703124979761123, "ce": 6.356205940246582, "genuineness": 4.400654315948486, "identity": 0.47373849153518677, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cf7489a5e28b9d37e569f69030201de759c79ead129f426df9a1630747c7f58a.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "cf94ebba5d0642d0f299017484073a6beda7aa31209771d2b89eae75e812ee12", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4ce26c1a0eba364dfc60f9be55c58ec660a458810f3ad3b4de0d9155f18c3825", "generation_seconds_batch": 22.510940287960693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5376843810081482, "target_z": 0.4707031190969942, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.6709577441215515, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/cf94ebba5d0642d0f299017484073a6beda7aa31209771d2b89eae75e812ee12.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "d01e3d696dc7e9ee3882661d55defbd71ec87bc2f6cc00cefcaa941854f4e7b2", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20186dac35e0fe03bbb8ca51c2e78cf815f73017e7c5dbe5a7db434b9b00a34e", "generation_seconds_batch": 16.45473897503689, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7911347150802612, "target_z": 0.9296874966268538, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.6541513204574585, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d01e3d696dc7e9ee3882661d55defbd71ec87bc2f6cc00cefcaa941854f4e7b2.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "d03fef135128c7af6db01882f278f5e6270d3df466211df74b1c132bab244fbc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "733ff18aa0e98cb12725165448bbcc2453fd73615f127cb502ec63ab25c9db67", "generation_seconds_batch": 21.70191879302729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6034736633300781, "target_z": 0.5898438292689351, "ce": 6.427689552307129, "genuineness": 4.231201171875, "identity": 0.4736776351928711, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d03fef135128c7af6db01882f278f5e6270d3df466211df74b1c132bab244fbc.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "d0574c11aeaf02a3d4fcb6dccc3f1ad79c1e74e6c4ca440bb97a1fa6673b45d5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "502847009706cea5cc229ad09dc9a4c94ac18aacfd3545db6b459d68ee2839a5", "generation_seconds_batch": 15.90621436201036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6772329807281494, "target_z": 6.156250013492585, "ce": 5.764476776123047, "genuineness": 3.8546390533447266, "identity": 0.2503128945827484, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d0574c11aeaf02a3d4fcb6dccc3f1ad79c1e74e6c4ca440bb97a1fa6673b45d5.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "d1120a3bc765d0d251149cc993ce7941e1ac21cbc12f88f7e3e5985b32b9cf43", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "50fa1e85911ab0266d74942d3fb835e7eab41d8c4cfee8f9a5af3fe7b0b7d38c", "generation_seconds_batch": 19.461320857983083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7954487800598145, "target_z": 0.9375000269851694, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.7017030715942383, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d1120a3bc765d0d251149cc993ce7941e1ac21cbc12f88f7e3e5985b32b9cf43.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "7d0c0f0fc2bd5ae0c3f56d54835d18a034e0b7c326896777e84b86bc047b47ee", "generation_seconds_batch": 16.82053467503283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06637461483478546, "target_z": -0.38281250337314615, "ce": 6.38003396987915, "genuineness": 3.9927117824554443, "identity": 0.265755832195282, "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_Astonishment_Surprise/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "d1abb2bb5f0456f5f81a5e05151519243f5f81d4303d6519608baa4f275ef17d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd55dc6957615066b776848e7f530c5e710c4781e0b836952e90d6e7d59aeb8b", "generation_seconds_batch": 20.63669736403972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3830184936523438, "target_z": 3.812499973014831, "ce": 6.1020402908325195, "genuineness": 4.18099308013916, "identity": 0.7993706464767456, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d1abb2bb5f0456f5f81a5e05151519243f5f81d4303d6519608baa4f275ef17d.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "d1baeb63e43263cb38391e9daf603721953f769129065d442c3120551447ce0a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "44120d971768181fda3312972f70517ee264c894255e8cfdf3b008e51cb51671", "generation_seconds_batch": 19.518389450968243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.468440294265747, "target_z": 2.156250013492585, "ce": 5.649308204650879, "genuineness": 4.143336772918701, "identity": 0.5410093069076538, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d1baeb63e43263cb38391e9daf603721953f769129065d442c3120551447ce0a.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "caeb6ded785e308d33dd18ac3ad3448fbf2a792cb98e6517bb5a97a9e8aa7d93", "generation_seconds_batch": 15.171072655008174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1103743314743042, "target_z": 1.5078125843286543, "ce": 6.324435234069824, "genuineness": 4.356721878051758, "identity": 0.5701891183853149, "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_Astonishment_Surprise/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "d2467c0f2a1f412ebee5a08c8826ab92755152fa28cc80ce4670fae20f9b0699", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18d1198f879c5c39aac093ddd6b69f1efbdcc14915661e8b26a84bb51726506a", "generation_seconds_batch": 21.407993337023072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4166717529296875, "target_z": 2.062500080955508, "ce": 6.038498878479004, "genuineness": 4.149612903594971, "identity": 0.571288526058197, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d2467c0f2a1f412ebee5a08c8826ab92755152fa28cc80ce4670fae20f9b0699.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "d25db025adc6c9bd577f28999e1e761dea4bd1a05ba4a6053f9c5664c9e009d0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9dd28d8636e740af9ef796518049f519e756490cd5afb0bd6a6bf52867e50aad", "generation_seconds_batch": 24.47826281597372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2907051146030426, "target_z": 0.023437483134269136, "ce": 6.316492557525635, "genuineness": 4.168440818786621, "identity": 0.28373196721076965, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d25db025adc6c9bd577f28999e1e761dea4bd1a05ba4a6053f9c5664c9e009d0.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "d27514aea0bcdb080f15513f8a06db82c01645f8c6f29397970dbb5730b6311b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "19bf816d387750c18e1b546f4c0c0c4bfaac55c793a1bb200a43a2cbb92416f6", "generation_seconds_batch": 16.433102365001105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.756622314453125, "target_z": 0.8671874696416845, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.673642635345459, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d27514aea0bcdb080f15513f8a06db82c01645f8c6f29397970dbb5730b6311b.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "d28126c55229e895fb9cd98e7b025a9861e82bb440ba279c5077c697b32979dc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a3237b2d0806f19f10201619de8609bd0528f9b83fe65133a88fc07cffb525e", "generation_seconds_batch": 15.92672590201255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5046708583831787, "target_z": 5.843749662685383, "ce": 5.990842819213867, "genuineness": 3.8671910762786865, "identity": 0.29903364181518555, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d28126c55229e895fb9cd98e7b025a9861e82bb440ba279c5077c697b32979dc.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "d2816199138861f6cda611dbaafd8da5feda497dc17cf801d255f9b8e58d623e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1c46b25cf5272b2305d748aa2058ea1fa83c74b0ac81412f46888e3c52d04834", "generation_seconds_batch": 16.748981571989134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3398778438568115, "target_z": 3.734374669431675, "ce": 6.205295085906982, "genuineness": 4.149612903594971, "identity": 0.509757399559021, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d2816199138861f6cda611dbaafd8da5feda497dc17cf801d255f9b8e58d623e.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "d2d816472792c2ae33c45e16f55c3e7cc2e761fb0d7305b997c7f874fdc33708", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4e0dd6a2767875a7bfe4ce775bee15c5042156f7a59a3c1b888b5e3642ee8528", "generation_seconds_batch": 23.56051128101535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3433328866958618, "target_z": 1.9296874966268538, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.4816485643386841, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d2d816472792c2ae33c45e16f55c3e7cc2e761fb0d7305b997c7f874fdc33708.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "d382cf45fab7f1f60c11d1b9fcd17d7efaf9794c50ba295ab5caefdcf8978f0f", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "40adec7ef4b5a09b54e9db8adfa09eb1449f7497fc06ee29cf95cd0292d0c9d9", "generation_seconds_batch": 14.693023168947548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2786221504211426, "target_z": 1.8124999730148306, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6877759695053101, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d382cf45fab7f1f60c11d1b9fcd17d7efaf9794c50ba295ab5caefdcf8978f0f.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "f1e0a67e472d703d5f753fb42d229b745e38b11a14f568f4d775eb79c2ea5ed1", "generation_seconds_batch": 17.09862250299193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.057746514678001404, "target_z": -0.3984375101194385, "ce": 6.1020402908325195, "genuineness": 4.519899368286133, "identity": 0.7592412233352661, "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_Astonishment_Surprise/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d423b1cd12080f125588fcf61709d75d72adb69ce416b356359fb60d6f38a159", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3bde5fc3aa540c5a9ff9eb070c7edfac096f910497c327d60b5dd43e48bb63d8", "generation_seconds_batch": 15.00159038498532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.314852714538574, "target_z": 5.499999622207628, "ce": 5.855817794799805, "genuineness": 4.086852550506592, "identity": 0.49513310194015503, "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_Astonishment_Surprise/d423b1cd12080f125588fcf61709d75d72adb69ce416b356359fb60d6f38a159.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": "d45f0963f7954110d9468c74bb4aa5861fdd8dac2c4047f2458416d50e2a8975", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e793c4d47e9f3f0b92af64010dce0e57a32377cb64fe8b196157a161832c674d", "generation_seconds_batch": 15.436860081041232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.452043294906616, "target_z": 3.937500026985169, "ce": 6.078212261199951, "genuineness": 4.030367851257324, "identity": 0.48538127541542053, "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_Astonishment_Surprise/d45f0963f7954110d9468c74bb4aa5861fdd8dac2c4047f2458416d50e2a8975.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "d50611cce54837aaeea195efa574fcf15c4c21df754fcdeb050482cefdb05097", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f057e146efa5860b2875a66eee361e1baeb9ea361c188d1338957dc145fc830c", "generation_seconds_batch": 23.337108843959868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.969728946685791, "target_z": 4.8749997841186445, "ce": 5.510311126708984, "genuineness": 3.7918784618377686, "identity": 0.7345877885818481, "hypothesis": "J'ai trouvé la petite boîte ! Elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d50611cce54837aaeea195efa574fcf15c4c21df754fcdeb050482cefdb05097.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "d72d249bb52a67f9eaf97c546df1843b4edd7715dfe6bf5ce7e293ab2879b4a8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "df304dd0f76e4227d0dda34369e0ccaef7129c973b86ec515c0e2ec9ce8c14d9", "generation_seconds_batch": 22.10031136998441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5128785967826843, "target_z": 0.42578123144769603, "ce": 6.181467056274414, "genuineness": 4.632867813110352, "identity": 0.5482026934623718, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d72d249bb52a67f9eaf97c546df1843b4edd7715dfe6bf5ce7e293ab2879b4a8.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": "d7505eee3b8f45a83e699f6224d790c354460bd900df99c910b1236e00fe8ec3", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93f728839b0626163476f8c682a373d340838dcab0998ae9b1e33a792fa2a62c", "generation_seconds_batch": 21.90396879101172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0715478658676147, "target_z": 1.4375000269851694, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.2458478808403015, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant. Ah.", "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_Astonishment_Surprise/d7505eee3b8f45a83e699f6224d790c354460bd900df99c910b1236e00fe8ec3.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "d77ebb034403599e7c9e1e374547d33a9816cabe8314d6ce3aa35331c19c6700", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2d5a4dceccd5d5e6f6202c7c856e7f0bd47d1f952932647da6144d94d5094419", "generation_seconds_batch": 21.858603856991976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3226218223571777, "target_z": 3.7031249797611228, "ce": 5.704906940460205, "genuineness": 4.017816066741943, "identity": 0.6362711787223816, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d77ebb034403599e7c9e1e374547d33a9816cabe8314d6ce3aa35331c19c6700.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "d7e7b7132777aa74c6be90ed1feae38861d034be3caa61569e7219388acbeae7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0c4613ae96bd27390173dbc538451fd80285606d435f89845b33464cb2357f4c", "generation_seconds_batch": 21.10818321898114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5564396381378174, "target_z": 5.93750002698517, "ce": 6.1020402908325195, "genuineness": 3.7918784618377686, "identity": 0.42947831749916077, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d7e7b7132777aa74c6be90ed1feae38861d034be3caa61569e7219388acbeae7.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "d80e15c9372caccf10d3bcdb43a9cb61c1952d63dd999c8810329188f38b9a68", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "892f235675113c5dfe2a2f322475c85883ef28bd59151012325006926de1cd97", "generation_seconds_batch": 17.0029988149181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0560100078582764, "target_z": 5.0312499595222455, "ce": 5.990842819213867, "genuineness": 3.911123275756836, "identity": 0.3305927515029907, "hypothesis": "The door is still open. I put your coat on the chair Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d80e15c9372caccf10d3bcdb43a9cb61c1952d63dd999c8810329188f38b9a68.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "d88430ae36ce84543a7b3eff8d0382748712868e61e1da98f7b2e780e42c1428", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "92e644f4227eb0a59ab218c07c56ad3d072cf15bbc196f7b511804c56cbf62b5", "generation_seconds_batch": 21.257258409052156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03509776294231415, "target_z": -0.4394531325895789, "ce": 6.165581703186035, "genuineness": 4.6705241203308105, "identity": 0.7022154331207275, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d88430ae36ce84543a7b3eff8d0382748712868e61e1da98f7b2e780e42c1428.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "d9b4388f43e292027cecb31dc5d54344173f59a3ac912da442d585f713a296a9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "78146297fa0d7b4dbdbedde70328a07b9ce4d2213e92e3b9a41d69d4f1f98376", "generation_seconds_batch": 17.027932845056057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.088804006576538, "target_z": 1.4687499325370765, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.7528255581855774, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d9b4388f43e292027cecb31dc5d54344173f59a3ac912da442d585f713a296a9.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "d9c082e7183ab6746b171344ce45496e5f9bd284ae48c18eb7c7e8063bd07bdf", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d6dee3e4118390b96445894f498281854fbf0a0cc3da1ce2c1559194f679da36", "generation_seconds_batch": 15.707480504061095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1952567994594574, "target_z": -0.14941407641422796, "ce": 6.332377910614014, "genuineness": 4.293961524963379, "identity": 0.3361207842826843, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/d9c082e7183ab6746b171344ce45496e5f9bd284ae48c18eb7c7e8063bd07bdf.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "da682418931819048b87f6fdcd3222bf0311510f1205c0e56c20add2182b131c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0bc2e7e03a322e39d637d80ac22ddd90fcf65607b22ee4107092c5df8daaf7d6", "generation_seconds_batch": 21.429450061987154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1017462015151978, "target_z": 1.4921875236120232, "ce": 6.340320587158203, "genuineness": 4.469690799713135, "identity": 0.5533065795898438, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/da682418931819048b87f6fdcd3222bf0311510f1205c0e56c20add2182b131c.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "daa7f3c77894fc98f94bc2eff5de56c9312aaa28b02f1f093ea6f08adc5d8cf2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "08bc38a34b1dbac0fbd295115045be394eb955217a551ec9ec5f92b2e668a548", "generation_seconds_batch": 23.586476730997674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9007041454315186, "target_z": 4.749999730148306, "ce": 6.316492557525635, "genuineness": 4.15588903427124, "identity": 0.6350854635238647, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/daa7f3c77894fc98f94bc2eff5de56c9312aaa28b02f1f093ea6f08adc5d8cf2.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "dab8f5940d76819c936d382719cc79946a3e7f9b473464a061f92866e8648e97", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2e2d715ffae8dc6b3541329e705d248abe2ebe92dbfb2e5b564f3a426f45fa6", "generation_seconds_batch": 21.299519303953275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4425560235977173, "target_z": 2.1093750472240465, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.6052546501159668, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dab8f5940d76819c936d382719cc79946a3e7f9b473464a061f92866e8648e97.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": "dac0c1f8928a8ee66391fb4b0718261722eb1a7468c221488a3f300d533c05f1", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d38dd108bb9bfc62c499872851d393120e3fc1f94a658c8cbd458a02ef46f8fe", "generation_seconds_batch": 20.186365406028926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4002745151519775, "target_z": 3.843749662685383, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.4457526206970215, "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_Astonishment_Surprise/dac0c1f8928a8ee66391fb4b0718261722eb1a7468c221488a3f300d533c05f1.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "dacc42e880d3212403049e35e5b299254569a399b421772481e9312d973505c0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3182ebbc8162dc6795fa17cdf02a970da5976ea9c3785b35b48a0218f993ee0b", "generation_seconds_batch": 22.662235931959003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4943245649337769, "target_z": 2.2031249797611228, "ce": 6.1020402908325195, "genuineness": 3.9676074981689453, "identity": 0.6797187924385071, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dacc42e880d3212403049e35e5b299254569a399b421772481e9312d973505c0.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "dadeb292e92a001d4a5ef31e453661e40cdf3727ca58bb6d6235861fc765dd2a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6ae748afc954eb8f21c756ec5b59feceab10e8f975788c0ffc4892e85d3c7493", "generation_seconds_batch": 13.844546045991592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9947541952133179, "target_z": 3.1093750472240465, "ce": 6.356205940246582, "genuineness": 4.362998008728027, "identity": 0.5732453465461731, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dadeb292e92a001d4a5ef31e453661e40cdf3727ca58bb6d6235861fc765dd2a.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "dafb6bc5f31194da72eb4d1836ad0752107e0daa01c051e0475761f95e373050", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "82b3d97238a77dd5f94455f967bd2aed0d92f7f9397fa0232e47d8d4ab9593dd", "generation_seconds_batch": 21.67378861794714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1932003498077393, "target_z": 3.4687499325370768, "ce": 6.022613525390625, "genuineness": 4.425758361816406, "identity": 0.562330961227417, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dafb6bc5f31194da72eb4d1836ad0752107e0daa01c051e0475761f95e373050.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "db175408978884033cba3353c17667948cd9d762ea7f4e8967a2ef8ba044e3db", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "77d85dfe35f4c550217c6ebab8931e291ada9441e2c68581448d3690aea7c258", "generation_seconds_batch": 20.805516547057778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7617956399917603, "target_z": 2.687500134925847, "ce": 6.181467056274414, "genuineness": 4.293961524963379, "identity": 0.2751461863517761, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/db175408978884033cba3353c17667948cd9d762ea7f4e8967a2ef8ba044e3db.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "1b1d2ca3b4e01686d2ee9f4bac134579e91f1071753fa42a762a2281f21e58cd", "generation_seconds_batch": 16.42527331900783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09225890040397644, "target_z": -0.3359375101194385, "ce": 6.4515180587768555, "genuineness": 4.381826400756836, "identity": 0.4401925504207611, "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_Astonishment_Surprise/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "dbd3766c6a87b7e2aef873d1d798ff017fe034a1e7565bdf8ac5e08cf63bca61", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c5bf6d5c7c0c8dd452141b27ba3602ecce9967f662474ba44c16eadbba231168", "generation_seconds_batch": 15.00159038498532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.675514578819275, "target_z": 2.531249959522246, "ce": 5.911416053771973, "genuineness": 4.15588903427124, "identity": 0.5572429895401001, "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_Astonishment_Surprise/dbd3766c6a87b7e2aef873d1d798ff017fe034a1e7565bdf8ac5e08cf63bca61.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "dbf4f0a9f4a154b3be6406d1bc093f9bb48a07b1298cce24d638ed39df803bbc", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "97a16b681660321039937d0d6047b70ac0834e54e04af01e2035f41797df945e", "generation_seconds_batch": 19.18653019098565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03833329677581787, "target_z": -0.4335937618060116, "ce": 6.483288764953613, "genuineness": 4.256305694580078, "identity": 0.4718230366706848, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dbf4f0a9f4a154b3be6406d1bc093f9bb48a07b1298cce24d638ed39df803bbc.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "dc2741fde3a035bb142a34277f7241f3c17bc91ec5b6eee17e8a40a01eec0b47", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "19030a6afe3358454e6b2ef2888e274634576ad0e913004d39d0313a5937cb8d", "generation_seconds_batch": 17.432979982928373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0551507472991943, "target_z": 3.218749824596399, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.6005913019180298, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dc2741fde3a035bb142a34277f7241f3c17bc91ec5b6eee17e8a40a01eec0b47.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "dc69d9a3525eaffc1e3bb1a2dff60dd2c9b022f6448cd41339d930728d2b378e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2fd5a75505303137eb0239ffcca0bc0a2267f1ee0fa2c5aaac6bbfc5e4518eda", "generation_seconds_batch": 21.468072083080187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7445393800735474, "target_z": 2.656250013492585, "ce": 6.300607204437256, "genuineness": 4.570107460021973, "identity": 0.4807808995246887, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dc69d9a3525eaffc1e3bb1a2dff60dd2c9b022f6448cd41339d930728d2b378e.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "dd0cd7c5e4f6519a904ade94aeb997b964a3979d79d213f497a3a9c59760a63c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2b00547700c2d41c80554593841948210589c60c387d53ca231d574555205fa7", "generation_seconds_batch": 19.41194987401832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5624901652336121, "target_z": 0.5156250067462923, "ce": 6.229123115539551, "genuineness": 4.7834930419921875, "identity": 0.6078592538833618, "hypothesis": "Die Tür ist noch offen. Ich hätt 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_Astonishment_Surprise/dd0cd7c5e4f6519a904ade94aeb997b964a3979d79d213f497a3a9c59760a63c.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "dd1a341b7fa94191f3f4e5e6bf39e731d6769026c4bfbf93aabe7659357d8648", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e30571713eb6673921f549fd71a7be5b340df68b43ff7749ddbfeaa6ba9f4f07", "generation_seconds_batch": 20.462730696075596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1289283186197281, "target_z": -0.26953124494028075, "ce": 6.173524379730225, "genuineness": 4.080576419830322, "identity": 0.3000890910625458, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dd1a341b7fa94191f3f4e5e6bf39e731d6769026c4bfbf93aabe7659357d8648.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "dd1ca2437b799817290d83e4a7e46eb06e8f81a72e041459488589f185790ca8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b0cad679ec38a8eabc4c0b364338e72b4a5f429b02c9ee6ee4735c7db978e8e", "generation_seconds_batch": 16.974026051000692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5719774961471558, "target_z": 2.343750094448093, "ce": 6.038498878479004, "genuineness": 4.293961524963379, "identity": 0.569943904876709, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dd1ca2437b799817290d83e4a7e46eb06e8f81a72e041459488589f185790ca8.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "dd2a9db1355fc2a66b99193a71b2617143fb9a4974db69614daa7d35c2407a28", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a5be3b63e1c39354e0fb40550c61fce6d683c6543f3b27d412601bacc91e13d7", "generation_seconds_batch": 21.05092143593356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6013165712356567, "target_z": 0.5859374561490998, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.7967469692230225, "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_Astonishment_Surprise/dd2a9db1355fc2a66b99193a71b2617143fb9a4974db69614daa7d35c2407a28.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "dd838f56282ff9879db50660a1bb16cf265f90907db628d9f2476bd720b12ac3", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7130adf9f70dc601d12f4e22e9a2336a2ebed8fcb51d471178d013216d3c3562", "generation_seconds_batch": 22.284963660058565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41257697343826294, "target_z": 0.24414060223126333, "ce": 6.443574905395508, "genuineness": 4.532451152801514, "identity": 0.42945629358291626, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dd838f56282ff9879db50660a1bb16cf265f90907db628d9f2476bd720b12ac3.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "dda316cc82bf58a257910648231da25396d3b397e6e7279ae708a3834e496f63", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c5d63823de983bfe20b9a21e374e724db0e40fee8bd8c9b40a36ed8246640879", "generation_seconds_batch": 21.099196358933114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8135641813278198, "target_z": 2.7812500674629232, "ce": 6.229123115539551, "genuineness": 4.231201171875, "identity": 0.4837495684623718, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dda316cc82bf58a257910648231da25396d3b397e6e7279ae708a3834e496f63.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "de661710a38c4a7d87693594a412b4fc340711d537a205b5a7b441450f20e326", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75f63fcee9158fe726b76c56338613a4b4a93b39229789c8bc164efee1cec7c0", "generation_seconds_batch": 21.012840693001635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288109302520752, "target_z": 3.6406247368945985, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.37252140045166016, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/de661710a38c4a7d87693594a412b4fc340711d537a205b5a7b441450f20e326.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "de7520e75f02b48675d616de4199c1ab8535c5ffd6e7d57f4fedf7a83d2ae1b5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4ce04739789050df48bf1d06a1265f871c0895cc75c7b9e1c7360da14bea0a44", "generation_seconds_batch": 16.99005096592009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4837587773799896, "target_z": 0.3730468674104211, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.35222935676574707, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/de7520e75f02b48675d616de4199c1ab8535c5ffd6e7d57f4fedf7a83d2ae1b5.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "deceb6d4760f591651a19fb92eedf969db8afc5d62ef293df36cf72c3538bae2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "91a883b8225b3abecae44ccd3625b03662c5a6a1233e1038048a211ad4694576", "generation_seconds_batch": 21.10992667300161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8135641813278198, "target_z": 2.7812500674629232, "ce": 5.824047088623047, "genuineness": 4.105680465698242, "identity": 0.578675389289856, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/deceb6d4760f591651a19fb92eedf969db8afc5d62ef293df36cf72c3538bae2.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "defc0a11d9059623959cde5058d2cf29872b566b35c640b08889e6bbaefb2d53", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4bd33eaf88669fde9ab05c86d2225ee93ce0d961ce4345420f5b668a32f7660", "generation_seconds_batch": 21.80989245302044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5383241176605225, "target_z": 4.093749770626061, "ce": 6.205295085906982, "genuineness": 4.149612903594971, "identity": 0.4538213610649109, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/defc0a11d9059623959cde5058d2cf29872b566b35c640b08889e6bbaefb2d53.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": "df0fe48ae70306221945250c5f0c6b91012158048006e938d0cc9c69c0491d11", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6cbb1450af16e820bed9c859e74c2e4595ccd207a51795792f77ac3e57f774a", "generation_seconds_batch": 15.314109888044186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227712631225586, "target_z": 3.531249743640891, "ce": 6.213237762451172, "genuineness": 4.494794845581055, "identity": 0.5431910157203674, "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_Astonishment_Surprise/df0fe48ae70306221945250c5f0c6b91012158048006e938d0cc9c69c0491d11.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "df476c2683837266eeb527aa38695bc72a3203e89acde23e34d1ae51ec34eeec", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "321fe75e3fda7a089490ebfa766731558925b807de5c3912dd5dd14db759385b", "generation_seconds_batch": 18.67473128705751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4002745151519775, "target_z": 3.843749662685383, "ce": 6.125868320465088, "genuineness": 4.218649387359619, "identity": 0.6099343299865723, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/df476c2683837266eeb527aa38695bc72a3203e89acde23e34d1ae51ec34eeec.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "df9d15bacd60e0056ab2a937175e7e4cdb50e9849485b9daf0d3148a9e5e1978", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2665303e45bf041405e0a806d77de2f5c06a0f4c7ff0ad23a20c4c00e771fb46", "generation_seconds_batch": 21.604554562014528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7531675100326538, "target_z": 2.6718750742092157, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.6282870173454285, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/df9d15bacd60e0056ab2a937175e7e4cdb50e9849485b9daf0d3148a9e5e1978.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "dfdf27b361de4f6c37ca77c46e9e7893f04361cc643fda3194fc033855eb2f34", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1fa11544ecc30be9b745d9b0b1555df3bad208db1a8b8946dfeb6ec922554ece", "generation_seconds_batch": 23.197484750067815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5029526948928833, "target_z": 2.218750040477754, "ce": 5.95112943649292, "genuineness": 4.105680465698242, "identity": 0.2615782916545868, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/dfdf27b361de4f6c37ca77c46e9e7893f04361cc643fda3194fc033855eb2f34.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e04e46b552014d8889b986ee9401912aeba0b5e41af5fe0ed9e1b0290ff2c261", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebcd4ddb230eff539d289f756b2c566e22bfac366ebb4eb99d0ce3862880d4a0", "generation_seconds_batch": 21.771616299985908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 6.260893821716309, "genuineness": 4.168440818786621, "identity": 0.7254129648208618, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e04e46b552014d8889b986ee9401912aeba0b5e41af5fe0ed9e1b0290ff2c261.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "e06772baea3f9f221f1c57b0d65e4fdcc736b9610e6585a56f610b35d8b6a81b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a9f2aaafb277f3fc5d7207e5612a8686b1b285d414c20cb28f479e898e18def", "generation_seconds_batch": 24.935629420913756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3139936923980713, "target_z": 3.687499919044492, "ce": 5.673136234283447, "genuineness": 3.948779582977295, "identity": 0.5485149621963501, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e06772baea3f9f221f1c57b0d65e4fdcc736b9610e6585a56f610b35d8b6a81b.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "e07ef3d1ae56374948450f77946c11c28248820626102c9b50c44eea5755f0c5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f32766c848130f50d9b643462d57eb377cefddd170c7663a03533604a59f9259", "generation_seconds_batch": 23.072266947012395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3292619287967682, "target_z": 0.09326171685260527, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.7188907861709595, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e07ef3d1ae56374948450f77946c11c28248820626102c9b50c44eea5755f0c5.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "e098e32f428cd951d275a2320c93da8856c77203c39d9bcd9f3d653c0599adaa", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "284c2008260fd0e22bb0b843943b7d599d381ab948ecb5f12ad40a446d2baa2b", "generation_seconds_batch": 18.200750636984594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7954487800598145, "target_z": 0.9375000269851694, "ce": 6.41180419921875, "genuineness": 4.293961524963379, "identity": 0.5769180059432983, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e098e32f428cd951d275a2320c93da8856c77203c39d9bcd9f3d653c0599adaa.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e160da58919aa2ce1c9e96942d20d63fc4e0987ceea46b133d089c52fdcd2fc8", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "feaf945d7516a3542c23c31bc0563d4b28c2ba6f7ffd0777dd9f78825c13d5bb", "generation_seconds_batch": 22.979478438035585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4363042712211609, "target_z": 0.28710941126132133, "ce": 5.967014789581299, "genuineness": 3.986435890197754, "identity": 0.40387967228889465, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e160da58919aa2ce1c9e96942d20d63fc4e0987ceea46b133d089c52fdcd2fc8.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e1a986d074e4e7bbf7e0fd35c78cb4f57db8a5a634af280479d530ed645bc216", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aff808e677f9c16bff8414e50224fcf3b64affc983afd511cb66b90ccfac0ba", "generation_seconds_batch": 17.139711315976456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6418612003326416, "target_z": 4.281249635700213, "ce": 5.665193557739258, "genuineness": 3.616149425506592, "identity": 0.5105130672454834, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e1a986d074e4e7bbf7e0fd35c78cb4f57db8a5a634af280479d530ed645bc216.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e20659eaf7576b5bf3d9512d6b0fcc73ee798482cc87c2dc89ac3cc92551a3d7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "37f1de03f4b391ac98b63999db21e995ba4012651da6bc2da33fc22bc1f4f312", "generation_seconds_batch": 22.425728995003738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3209034502506256, "target_z": 0.07812497976112297, "ce": 5.927301406860352, "genuineness": 4.331617832183838, "identity": 0.634409487247467, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e20659eaf7576b5bf3d9512d6b0fcc73ee798482cc87c2dc89ac3cc92551a3d7.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "e2445c7a9fb0d1122acbd4d92acc61e19deb7a0dc7cbd02ff57ba7e8da86d461", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1fd928ff2cd94417afd81407560a0ca9e2d4efb13ffd031bcb95e6e9339810d3", "generation_seconds_batch": 23.524087914964184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5646471977233887, "target_z": 0.5195312719254501, "ce": 6.229123115539551, "genuineness": 4.1998209953308105, "identity": 0.7821438908576965, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e2445c7a9fb0d1122acbd4d92acc61e19deb7a0dc7cbd02ff57ba7e8da86d461.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "e2504493e2edbfe7deccbfa772238998f5b69f2a6750ef246ff8af8bb93a4d1d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cfce379fae63d70c2a892b9e5e4f6d12e74a059d012d154854f755dd2113db58", "generation_seconds_batch": 23.432178449002095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1837130784988403, "target_z": 1.6406249527759535, "ce": 6.1020402908325195, "genuineness": 4.086852550506592, "identity": 0.4103257656097412, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e2504493e2edbfe7deccbfa772238998f5b69f2a6750ef246ff8af8bb93a4d1d.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "e27610cff94ee2d121d5dfe267ccc2a25e9985c224a406679584c8af89dd03b1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cd4b560e0bcdfbaa01c0516706ce49db54de0755ca27c9e72a72eccd1036f4b9", "generation_seconds_batch": 21.51751635200344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9007041454315186, "target_z": 4.749999730148306, "ce": 6.038498878479004, "genuineness": 3.961331605911255, "identity": 0.44312793016433716, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e27610cff94ee2d121d5dfe267ccc2a25e9985c224a406679584c8af89dd03b1.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "e285a0e880d3e096085fc5c115a5c7aacf04acd26e5a6a5b16d2a7f5d6f25030", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0dc5b6147e00e6674f935e740e60aa928e57b250d170dc879ef549dc8ee5069", "generation_seconds_batch": 24.39473810105119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.012010335922241, "target_z": 3.1406249527759535, "ce": 6.117925643920898, "genuineness": 3.9425034523010254, "identity": 0.5866167545318604, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e285a0e880d3e096085fc5c115a5c7aacf04acd26e5a6a5b16d2a7f5d6f25030.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "e2a10d41e36cf2615a792956cac3e1bc20ca3f89a8e68a2dd25d0138bd8169a7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "56d867405274160338fc541f6fd731b830613b75a42c59de5ff6ccf9ce1d63c6", "generation_seconds_batch": 17.190116959041916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5719774961471558, "target_z": 2.343750094448093, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.38518449664115906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e2a10d41e36cf2615a792956cac3e1bc20ca3f89a8e68a2dd25d0138bd8169a7.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e2be04b05bc9281b2f66ad1292904a855c95b1a4e37d7011f4db279bc2923bd9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "076c12b930d05004582ee32b178c6576919ba5b5eae7a477434c240abdb7d603", "generation_seconds_batch": 21.10818321898114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.107778549194336, "target_z": 5.124999892059322, "ce": 6.054384231567383, "genuineness": 3.9550557136535645, "identity": 0.3155549168586731, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e2be04b05bc9281b2f66ad1292904a855c95b1a4e37d7011f4db279bc2923bd9.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "e2fd59c0d660e5769949a7129a59e104e948c0638f4048a24cb97bb002148f10", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "773fa2dca576f24f52eeb9c6772243318c8bdb116f752af1b3d0002294da0a72", "generation_seconds_batch": 14.521804051008075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907874822616577, "target_z": 2.0156251146869697, "ce": 6.1894097328186035, "genuineness": 4.306513786315918, "identity": 0.4170944392681122, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e2fd59c0d660e5769949a7129a59e104e948c0638f4048a24cb97bb002148f10.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e3853576e23b810a01f11f0a83d0e6371ae2b526b010cc4c6b4104dcb9d123a0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "563194c86ea886e40e3345cc3074098d29eca9ade01c4d36e4c865c6e2f58991", "generation_seconds_batch": 21.055848810006864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.710886001586914, "target_z": 4.4062496896705525, "ce": 6.038498878479004, "genuineness": 4.030367851257324, "identity": 0.40737706422805786, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e3853576e23b810a01f11f0a83d0e6371ae2b526b010cc4c6b4104dcb9d123a0.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "e3b69a4499d6dacb0e180451d94777fc2649f213337e2c8d613c71dd8d231b21", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3ed7d23bad6bea8d0b3e9c1205d18fd475c55e9ce18d5bb4a3bb6cc71667efa7", "generation_seconds_batch": 19.18653019098565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847217321395874, "target_z": 1.031249959522246, "ce": 6.499174118041992, "genuineness": 4.7332844734191895, "identity": 0.4856449365615845, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e3b69a4499d6dacb0e180451d94777fc2649f213337e2c8d613c71dd8d231b21.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e3ca0ea237cfde484370b425a8cec8bb50f899554b67d9c83526f83ee295845a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "186dd60bd6583f2e3860214df670d51ebb90b6351eef7d2cad35ed05d5ea328d", "generation_seconds_batch": 23.34059741697274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.694489002227783, "target_z": 6.1874997031631365, "ce": 5.450741291046143, "genuineness": 3.7542223930358887, "identity": 0.5741963386535645, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e3ca0ea237cfde484370b425a8cec8bb50f899554b67d9c83526f83ee295845a.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "e4148cbc5db2b8ea1c61a0702a5c2d15b19408be05548a88e1a73c3be594df3d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d177c935d032b35c8e77132dc56f47ba78965d1c24e51c7022ce935c7e769a4c", "generation_seconds_batch": 22.284963660058565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15966591238975525, "target_z": -0.21386718201863747, "ce": 6.403861999511719, "genuineness": 4.2751336097717285, "identity": 0.4406605660915375, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e4148cbc5db2b8ea1c61a0702a5c2d15b19408be05548a88e1a73c3be594df3d.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e44bc2a5e2641f4aefdb21bfc5553eaf3c4dc7ddd78a554cb3f367d571cf7de6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4954e9c40afa77a8e1c826abf90243c2af27bff3e560b641f1842da110b7acf1", "generation_seconds_batch": 22.927076056948863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9179604053497314, "target_z": 4.781249851581569, "ce": 6.165581703186035, "genuineness": 3.9048471450805664, "identity": 0.39287108182907104, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e44bc2a5e2641f4aefdb21bfc5553eaf3c4dc7ddd78a554cb3f367d571cf7de6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "e48a14ce39b71238c97169933866f7d87b06dbb5e5ef21b410d88a0e34c6ea26", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1a62ca76d5125c8ca394f73e5c847416272dccf8536538dd90b0c1179af03fae", "generation_seconds_batch": 21.18676798196975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968869924545288, "target_z": 3.062500080955508, "ce": 5.831989288330078, "genuineness": 3.923675537109375, "identity": 0.6695630550384521, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e48a14ce39b71238c97169933866f7d87b06dbb5e5ef21b410d88a0e34c6ea26.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": "e4ad6be6ded7b1231a3c2a16fcf27e82a21d67ba64c1cc02793610c7e8396169", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3871ca5559303969a2823c490984e3289c91858e5cc22919b5b4640b33088fba", "generation_seconds_batch": 16.63207096804399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4244406223297119, "target_z": 0.26562500674629236, "ce": 6.157639026641846, "genuineness": 4.18726921081543, "identity": 0.5298322439193726, "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_Astonishment_Surprise/e4ad6be6ded7b1231a3c2a16fcf27e82a21d67ba64c1cc02793610c7e8396169.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "e4cbbf9d10826619a9dfe2ac4a517bc2c8961c84e5cd3038164bfc995d4cf18e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d6a6353f9882ac37943918507bcffae7b711685e9d6fc6e8a78216d63e38c0d9", "generation_seconds_batch": 23.277685089968145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4434151649475098, "target_z": 3.9218749662685384, "ce": 6.0305562019348145, "genuineness": 4.256305694580078, "identity": 0.5597965717315674, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e4cbbf9d10826619a9dfe2ac4a517bc2c8961c84e5cd3038164bfc995d4cf18e.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e5a4c815a631abc7f3f2a67eaa378b7d2115f1e0f7ce1ffe6681e3371c546ef7", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "46ae68c82d5e2cad9f1eeb5856380d04de7f0982d0ce7293f825868f3d17bd02", "generation_seconds_batch": 17.803560441941954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7738785147666931, "target_z": 0.8984374831342692, "ce": 5.621508598327637, "genuineness": 3.7793264389038086, "identity": 0.4626215100288391, "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_Astonishment_Surprise/e5a4c815a631abc7f3f2a67eaa378b7d2115f1e0f7ce1ffe6681e3371c546ef7.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "e5dffa30febc26185263d5a55c4b0e7c9bedcf48d2c72cb812c8391244be6d20", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0b9f2648568633c7ae61e53edb96793fafe0cbe91e770911164006a3362cb8cf", "generation_seconds_batch": 19.65854459500406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.952472686767578, "target_z": 4.843749662685383, "ce": 5.780362129211426, "genuineness": 3.9048471450805664, "identity": 0.41151612997055054, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e5dffa30febc26185263d5a55c4b0e7c9bedcf48d2c72cb812c8391244be6d20.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "e5f5388c472086e31ecb7d8d96bf0cc2dfb1d855fd3216bfc02e8293e2ed519e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "73dcf5a340745bef5c9b55ff680c52f229f1d837301c1c71e113e86f5c354d44", "generation_seconds_batch": 15.49550167308189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.867051124572754, "target_z": 6.500000053970338, "ce": 5.974957466125488, "genuineness": 3.973883628845215, "identity": 0.6274327635765076, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e5f5388c472086e31ecb7d8d96bf0cc2dfb1d855fd3216bfc02e8293e2ed519e.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "e5fa710635be5aaf9734a8394f88d6dcdd136d558b439146c14bebfdcad42161", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "42f731525b4457f20ba655ef51a793b8ae5c85a8b269e3839d42817e333441e5", "generation_seconds_batch": 23.072266947012395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7048537731170654, "target_z": 0.7734375371046079, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.6685453653335571, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e5fa710635be5aaf9734a8394f88d6dcdd136d558b439146c14bebfdcad42161.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "e61b2f4b061c37063b9ccdb57e7b02aa75fde908124d2fda3bcf1e56ea0faf87", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4388cd06d7884b1f75d6eab6717609c973600fafce576514937558222734369f", "generation_seconds_batch": 21.689948641113006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5555803775787354, "target_z": 4.124999892059322, "ce": 6.0146708488464355, "genuineness": 3.8044304847717285, "identity": 0.5799158811569214, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e61b2f4b061c37063b9ccdb57e7b02aa75fde908124d2fda3bcf1e56ea0faf87.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "e67357e84cafa766edd87c57437eda4f6df0f03aaed362091c3a07cc590a3444", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e21697eb1174b500b89bfdebd441a45e8df3103a9f4a45d12b306ca6d6d282f5", "generation_seconds_batch": 21.680496993940324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2095973491668701, "target_z": 1.687499919044492, "ce": 6.24500846862793, "genuineness": 4.369274139404297, "identity": 0.42083320021629333, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e67357e84cafa766edd87c57437eda4f6df0f03aaed362091c3a07cc590a3444.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "e6745748948d8836a68b531636b82df91f2d4e84bce907c9038daf8670943190", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0bbf42c55cfdef9610dc2bc54e040e793565ed755767a69a6fd2b8e73701e9e2", "generation_seconds_batch": 20.372685540933162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9516136646270752, "target_z": 3.031249959522246, "ce": 6.229123115539551, "genuineness": 4.168440818786621, "identity": 0.20676454901695251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e6745748948d8836a68b531636b82df91f2d4e84bce907c9038daf8670943190.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e6e9c1b7b44c49c54cdf56e8878510e3906e91b529aaf6c936e9593fb8dd89e9", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "124c3cceb4fdfd8126e65913ff2146750e64f84e89ea644bfc2a3b9f1a315962", "generation_seconds_batch": 15.748628080938943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2630841732025146, "target_z": 5.4062496896705525, "ce": 6.23706579208374, "genuineness": 4.086852550506592, "identity": 0.23318657279014587, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e6e9c1b7b44c49c54cdf56e8878510e3906e91b529aaf6c936e9593fb8dd89e9.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "0db025057bb9e8087b2070ac685cb0b767cae567634b1d8dd0a6d4300f802641", "generation_seconds_batch": 16.425562530057505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847217321395874, "target_z": 1.031249959522246, "ce": 6.3641486167907715, "genuineness": 4.281409740447998, "identity": 0.3014379143714905, "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_Astonishment_Surprise/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e734d2a27fd5c1bc7b67797c823faa24f150439120945a19a44bbdbc67fef290", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b1dc373b4cbc4946a9fbfcb0b4e6a8bb37fbf4bc3e7c97525d09759dfb9c4ed8", "generation_seconds_batch": 22.72283869201783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8817297220230103, "target_z": 1.0937499865074154, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.5245358943939209, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e734d2a27fd5c1bc7b67797c823faa24f150439120945a19a44bbdbc67fef290.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "e7fb70e194e05451649113d34eb089d80c5bbfb044d60d35b598ba7498aa6960", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "522c76b7e7f616c1956669b4ad71e538cb29a974054bb41a82063e73485fb48f", "generation_seconds_batch": 15.92672590201255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 5.696964263916016, "genuineness": 3.747946262359619, "identity": 0.6828851699829102, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e7fb70e194e05451649113d34eb089d80c5bbfb044d60d35b598ba7498aa6960.mp3" }, { "id": "emo_Astonishment_Surprise-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-0", "key": "e87728d6feda8c5d90fe05e3e3e85d014c6ab71cee412cdb592baba7f5543eff", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La puerta sigue abierta.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bb6f55ca331bdb1fec7a10275251749a172bbf88bc745be8bfc334b33d490771", "generation_seconds_batch": 21.05020833807066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7626547813415527, "target_z": 4.500000053970338, "ce": 5.7684478759765625, "genuineness": 3.9927117824554443, "identity": 0.47914746403694153, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e87728d6feda8c5d90fe05e3e3e85d014c6ab71cee412cdb592baba7f5543eff.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "e8f8655f2a3022266e4d94a81300fdd70ff0f3a3daf63b056dcdc901d8fa8096", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7282d0f66dbf9e49b758abc9ef7577847a7c5336a07c3cb3844e20ac1a287dd9", "generation_seconds_batch": 22.781388895004056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6099447011947632, "target_z": 0.6015625168657308, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.52167809009552, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e8f8655f2a3022266e4d94a81300fdd70ff0f3a3daf63b056dcdc901d8fa8096.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "e94e97ee1bbcaa69c7926e87d5c0a12a7bd028b3fde67adfc683a7c8f2302ad2", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "54845cd245d5d89f36157078bb818ceed1e9721b2986d9491f29a65bc0b3b5b8", "generation_seconds_batch": 22.739051164942794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.590951919555664, "target_z": 5.999999838088984, "ce": 6.006728172302246, "genuineness": 3.7667744159698486, "identity": 0.2587885558605194, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e94e97ee1bbcaa69c7926e87d5c0a12a7bd028b3fde67adfc683a7c8f2302ad2.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "e9731aed58c634f5717f41940575dc090374be27fd724dd500ed57a2b3871f8a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8297c31de2ff6db50007d4870cfe43701196c2094a3abf561824cb047a4aeaff", "generation_seconds_batch": 23.80222339904867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1837130784988403, "target_z": 1.6406249527759535, "ce": 6.324435234069824, "genuineness": 4.287685871124268, "identity": 0.4688420295715332, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/e9731aed58c634f5717f41940575dc090374be27fd724dd500ed57a2b3871f8a.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "246ae6a2485aa613e91a96e923b024e2e99ded79d938ce16665e410edadf6bdb", "generation_seconds_batch": 16.859611344058067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4837587773799896, "target_z": 0.3730468674104211, "ce": 6.459460258483887, "genuineness": 4.281409740447998, "identity": 0.5503051280975342, "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_Astonishment_Surprise/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "ea534c7768b8198b337baa7104b16b2121991f7980731c4f90b86989b4d75ded", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dd8c608bca234339a0480f68e2803ddb30367118a9993153f264e235ba6e221f", "generation_seconds_batch": 23.145758813945577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9421263933181763, "target_z": 1.203124979761123, "ce": 6.141753673553467, "genuineness": 4.262581825256348, "identity": 0.4768070876598358, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ea534c7768b8198b337baa7104b16b2121991f7980731c4f90b86989b4d75ded.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "ea73276fe14d0dfa4d4db64fb6842022877c49d1a716c6bbdb1bc4277d6ed393", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "478da305905515f2b5ba6360b0200dd89f7c8b632255d7cee79681d6a2c9e9ee", "generation_seconds_batch": 22.847708059009165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.088804006576538, "target_z": 1.4687499325370765, "ce": 5.9431867599487305, "genuineness": 4.174716949462891, "identity": 0.7515428066253662, "hypothesis": "J'ai trouvé la petite boîte. Elle était prêvée 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_Astonishment_Surprise/ea73276fe14d0dfa4d4db64fb6842022877c49d1a716c6bbdb1bc4277d6ed393.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "ea90b8db030e72057ff13ee37bf492f1d9a87b23ff2b167161385ec01d96f905", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1cb8c90d6d69043de18e78b400be36be829861c5e80fa7fc5ec0d55edae4e62d", "generation_seconds_batch": 16.564259089995176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25403571128845215, "target_z": -0.04296875505971926, "ce": 6.221180438995361, "genuineness": 4.545003414154053, "identity": 0.7240293622016907, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ea90b8db030e72057ff13ee37bf492f1d9a87b23ff2b167161385ec01d96f905.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "eb83a5b3bd58fd2c4fe88ab7af36724eb932a512fd954f132d2517570b3a1a27", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28c35a0f0c0ecd45efee34d365b51ebfbce3cffc41d00524bb855e41d622ba65", "generation_seconds_batch": 20.88876463996712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1880271434783936, "target_z": 1.6484374831342692, "ce": 6.09409761428833, "genuineness": 4.118232727050781, "identity": 0.7411403656005859, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/eb83a5b3bd58fd2c4fe88ab7af36724eb932a512fd954f132d2517570b3a1a27.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "f60a650a0ec9b2daa11d3a667df7bf33161c1ae58d25382fac6226bda0479215", "generation_seconds_batch": 17.790758160990663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011278241872787476, "target_z": -0.5234374831342692, "ce": 6.1894097328186035, "genuineness": 4.3504462242126465, "identity": 0.8033071756362915, "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_Astonishment_Surprise/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "ec04c1388a3bf1d7f34bed20bf0478987c2a3a3c82a8f62cff177511c8a9af65", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e16ef919f243dfc5c71ba4a21e7f6f75bda740d05efdb86fd6f2e4b7f3d2e8c", "generation_seconds_batch": 22.210731366067193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.136258602142334, "target_z": 1.5546875505971927, "ce": 5.95112943649292, "genuineness": 4.218649387359619, "identity": 0.43081289529800415, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ec04c1388a3bf1d7f34bed20bf0478987c2a3a3c82a8f62cff177511c8a9af65.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "eca47c2f41e23379448367361c5ce4eaf0decf75fbc4ca46af8cf872b2c77f5d", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7ef1cd30b36a90c23038115a067bbc69808a871364f5014b7764c422912719e6", "generation_seconds_batch": 16.748981571989134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.590092658996582, "target_z": 4.1874997031631365, "ce": 6.340320587158203, "genuineness": 4.093128204345703, "identity": 0.6110683083534241, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/eca47c2f41e23379448367361c5ce4eaf0decf75fbc4ca46af8cf872b2c77f5d.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "ed0159f065917df5362763c1b997e5381a9e3d49819e86520f1ae4108a14087c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6f3c29309ce4f05af2a5343333ac3889c8c225503ce47ad47c33240002bd21e6", "generation_seconds_batch": 22.249897071975283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2804592549800873, "target_z": 0.0048828044887778395, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.5837816596031189, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ed0159f065917df5362763c1b997e5381a9e3d49819e86520f1ae4108a14087c.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "ed3594c3074b91d5be5ef8196cd31c467ad04fbd955b441c5f7b774257c238c5", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "48b025b29a665cda465f57451d3f41636474abfbe585a4d8543b6e9896484ea4", "generation_seconds_batch": 22.53617779398337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44493234157562256, "target_z": 0.30273436403727494, "ce": 6.141753673553467, "genuineness": 3.9801597595214844, "identity": 0.35535597801208496, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ed3594c3074b91d5be5ef8196cd31c467ad04fbd955b441c5f7b774257c238c5.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "ed3d4379b38e5ce2caab9aae21c84f439c7d05e6ed06ca7e56c3aa64d6afd07e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fead254351da23fc59008dd758247ee1f530fe5dcc06fd0a6f0d05813c19217a", "generation_seconds_batch": 15.919007880031131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4434151649475098, "target_z": 3.9218749662685384, "ce": 5.919358730316162, "genuineness": 4.086852550506592, "identity": 0.6370030045509338, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ed3d4379b38e5ce2caab9aae21c84f439c7d05e6ed06ca7e56c3aa64d6afd07e.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": "ed4447bdf7b4440fe93fffd6d795f147b737b46df737a723d49d2180c8594e19", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d6fa2ca02cac12a809e9b6c2f5b6052910637d7188a04c2e05c1f4c3cdb9554", "generation_seconds_batch": 17.080025703064166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2018284797668457, "target_z": 3.4843749932537076, "ce": 6.2767791748046875, "genuineness": 4.3504462242126465, "identity": 0.5609147548675537, "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_Astonishment_Surprise/ed4447bdf7b4440fe93fffd6d795f147b737b46df737a723d49d2180c8594e19.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "edd377c7a7c6634c71db52cc4caed0f888290b50e4b5043868340cb130b7b268", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "60fadce1f0bc3aa9dbf2c716ec32c7384cf21e1c02d937f83846051f575f2630", "generation_seconds_batch": 21.41529958997853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.675514578819275, "target_z": 2.531249959522246, "ce": 6.038498878479004, "genuineness": 4.20609712600708, "identity": 0.5637704730033875, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/edd377c7a7c6634c71db52cc4caed0f888290b50e4b5043868340cb130b7b268.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "ee440e56b3c46df1518deff921d9661340f98cf9ad8ba1ba41e402ed2ad01068", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "460185362897708f587daf800f4b38a806a7b47e310cc007e976cb1e7772888d", "generation_seconds_batch": 17.366010625031777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0560100078582764, "target_z": 5.0312499595222455, "ce": 5.824047088623047, "genuineness": 3.8797430992126465, "identity": 0.5254196524620056, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ee440e56b3c46df1518deff921d9661340f98cf9ad8ba1ba41e402ed2ad01068.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "eedc4a5d5396c2438dab9cc7d3b1aae604c7c7619771abee30ce6adde365a965", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7eb9feb92aa36097c3614b6f175dcf04ce0c3982e18d971d8aade091d68ba914", "generation_seconds_batch": 20.713296809000894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0038209259510040283, "target_z": -0.49609373482084224, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.7111223340034485, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/eedc4a5d5396c2438dab9cc7d3b1aae604c7c7619771abee30ce6adde365a965.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "eefaff26b7cbf54a107c9b17918a3dbe180fdf628257937b6d4788a9e6ca7d3f", "bucket": "emo_Astonishment_Surprise", "phase": "wording", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6b840e07040377925da46673f460ed8c6c657634f32b8fe6c05117fb83041784", "generation_seconds_batch": 14.066625809995458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35433733463287354, "target_z": 0.13867187415671345, "ce": 6.356205940246582, "genuineness": 4.8588056564331055, "identity": 0.6549631953239441, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/eefaff26b7cbf54a107c9b17918a3dbe180fdf628257937b6d4788a9e6ca7d3f.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "ef8071167675e19670dd1ab5be73fbe19c6b08c2e657ef0152b3ba88a342af4b", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "44cd9c3e6dd286e3b76d60c4cc8da578fea76f24bb7405d348dbbc8be8da0de2", "generation_seconds_batch": 21.407993337023072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6927708387374878, "target_z": 2.562500080955508, "ce": 6.181467056274414, "genuineness": 4.319066047668457, "identity": 0.7965471148490906, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/ef8071167675e19670dd1ab5be73fbe19c6b08c2e657ef0152b3ba88a342af4b.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "efcd74f68faee7fb235f7dc705b3e04f44279805bd3fac0f6d1d1d4d7a942182", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3b91e9f2ef7af39ec48146d33502d669f708598bfd252541bdbd348a7db0df8d", "generation_seconds_batch": 17.201127987005748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5555803775787354, "target_z": 4.124999892059322, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.5469170808792114, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/efcd74f68faee7fb235f7dc705b3e04f44279805bd3fac0f6d1d1d4d7a942182.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "f03b499093c57491d4f54fe1330b5fe3ceabc8b4993ade9bc7515a4648e73c69", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "23dbdc2feb37540be408d4b73063864eba87654413a6d32fbca1ac3c0247a8bb", "generation_seconds_batch": 25.65894447104074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2363407611846924, "target_z": 3.546874804357522, "ce": 5.8875885009765625, "genuineness": 3.9927117824554443, "identity": 0.6059166789054871, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f03b499093c57491d4f54fe1330b5fe3ceabc8b4993ade9bc7515a4648e73c69.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "f0cc42807008b3bb31d34e0d965c4d5b7c9181c379996820ad19a0c5d59ae096", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4c515eee53da4c4dc0d34a21034d348086cc83e030a6f31ed3ba88e56b5e1ab9", "generation_seconds_batch": 21.78619439608883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35649436712265015, "target_z": 0.14257813933587124, "ce": 6.507116317749023, "genuineness": 4.174716949462891, "identity": 0.5193750262260437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f0cc42807008b3bb31d34e0d965c4d5b7c9181c379996820ad19a0c5d59ae096.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": "f10330f646fa65dda7dc844bdf28e6ba10b58f8bfa4e548cae27afc25d0f1bb5", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "49195f7b8f1d390618b54b04b7fc8acf457ff981d65bfe96f8c1cb542a0ac765", "generation_seconds_batch": 22.768792065093294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1586880683898926, "target_z": 3.406250121433262, "ce": 6.086154937744141, "genuineness": 3.9425034523010254, "identity": 0.3811068534851074, "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_Astonishment_Surprise/f10330f646fa65dda7dc844bdf28e6ba10b58f8bfa4e548cae27afc25d0f1bb5.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "f114ac45ff19fde591cf35d946c493fafce3b7badf60d419fe426522a922e9c1", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0dc664b67472324ad5654e9f03f3d3186610de11f04ec9ebb2ef7284fc6a0f6e", "generation_seconds_batch": 22.54559558897745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9429856538772583, "target_z": 3.0156251146869697, "ce": 6.197352409362793, "genuineness": 3.936227321624756, "identity": 0.28512001037597656, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f114ac45ff19fde591cf35d946c493fafce3b7badf60d419fe426522a922e9c1.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "f17e109c0363f109975be8380ffd73b663af1dae58ee8a606b56ced38050c41a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "29c71e4a699c7677a1352bef9e7e707b11833a9f9a9339c556e62092aeeb3a98", "generation_seconds_batch": 22.99911767593585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8385891914367676, "target_z": 1.015624898805615, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.5141187310218811, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f17e109c0363f109975be8380ffd73b663af1dae58ee8a606b56ced38050c41a.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "d55978d961098af87325c0b9b4462d683b0d5c0cb16e93da41fda5c3d0bb5522", "generation_seconds_batch": 16.213999754050747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30041173100471497, "target_z": 0.04101562247014037, "ce": 6.197352409362793, "genuineness": 4.13078498840332, "identity": 0.6246576905250549, "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_Astonishment_Surprise/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "f24df6a935a645932705ef0424a81e88ca395ce71fc9627a1d150f659e4a87a6", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a01dab64cdae80e7b9aa931d0ec57c2ebe5d3b5963779e743d54ee24934e4f26", "generation_seconds_batch": 22.84544134803582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3395077884197235, "target_z": 0.11181639549809658, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.5642648935317993, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f24df6a935a645932705ef0424a81e88ca395ce71fc9627a1d150f659e4a87a6.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "f2b40362ce22b7f7ea65385c0a8df4d6f8567414883f7aec4694ab2c04b12fc4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e7221a3ced9387bc24012eb71bb732a0470333f0d95ac9c843f00c6c12d21b6b", "generation_seconds_batch": 15.790743842022493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11382915079593658, "target_z": -0.29687499325370764, "ce": 6.109982967376709, "genuineness": 4.532451152801514, "identity": 0.4646803140640259, "hypothesis": "La porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, quand tu es prêt, et du rêne ici, bébé.", "wer": 0.5555555555555556, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f2b40362ce22b7f7ea65385c0a8df4d6f8567414883f7aec4694ab2c04b12fc4.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "f2e86c3a53aeea130675a5d471f7f374437d80ec11db71e1f6161d9b264079f0", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ccb24848df054119cbb3ba0ace611e74c56acd21fd9ce789d4bf803dd9acdbf2", "generation_seconds_batch": 21.555165598983876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2441097497940063, "target_z": 1.7499999460296611, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.683046817779541, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f2e86c3a53aeea130675a5d471f7f374437d80ec11db71e1f6161d9b264079f0.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "f34006281043a556fd4cd287013a756692baed25b413713f77c62ccc9295b900", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64aafc2ecbd00f5bd0bb0b52d40627398a8af9e87a174eca690c6b70303a574b", "generation_seconds_batch": 23.04213024605997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3138931393623352, "target_z": 0.06542969888436834, "ce": 6.213237762451172, "genuineness": 4.325342178344727, "identity": 0.6663686633110046, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f34006281043a556fd4cd287013a756692baed25b413713f77c62ccc9295b900.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "f36408f3a9104ce277343b634a289c9a3e4019a71d287fb96ba9ad3cb8116e92", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2875f5c5c99338a6c69bf8aea045ff2ebfd94d05d2d52d553c95671d7ab369e3", "generation_seconds_batch": 21.702934039058164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4546389579772949, "target_z": 0.32031250337314615, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.6159601211547852, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f36408f3a9104ce277343b634a289c9a3e4019a71d287fb96ba9ad3cb8116e92.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "f3c5fc371a2d293107837eb7838f0b39853097fa44280a1e7ede11ca5ecd4326", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7a5a7242ba3a6c8dee9e7983bb757326ee74a7e7cbb589c3912616a2db931402", "generation_seconds_batch": 19.167389909969643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4175307750701904, "target_z": 3.874999784118645, "ce": 6.038498878479004, "genuineness": 3.8420867919921875, "identity": 0.4953862726688385, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f3c5fc371a2d293107837eb7838f0b39853097fa44280a1e7ede11ca5ecd4326.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": "f3d24e2ecc90fd62acdda9449cc4fd2136658b65445150e92370cd46692583e9", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99fe2b2907227eed7df48d4476f74da0981377b472c488c189c52e830c2618e4", "generation_seconds_batch": 16.02773202001117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.612101674079895, "target_z": 0.6054686741042111, "ce": 6.23706579208374, "genuineness": 3.9801597595214844, "identity": 0.3211931884288788, "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_Astonishment_Surprise/f3d24e2ecc90fd62acdda9449cc4fd2136658b65445150e92370cd46692583e9.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": "f3f845c4aa125b0793c04a8c2b26d9e213e5cc1e133934adc1af256dd0098bf4", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "434c160887c37ed0ee84c809c1b267626633340fae7f88b97160f6b530ab8c1a", "generation_seconds_batch": 17.391301196999848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0214974880218506, "target_z": 4.968749716655721, "ce": 6.086154937744141, "genuineness": 4.030367851257324, "identity": 0.5324175953865051, "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_Astonishment_Surprise/f3f845c4aa125b0793c04a8c2b26d9e213e5cc1e133934adc1af256dd0098bf4.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "f4ddef43163bcd1946a449af3f92f9f00287d562cfc4ecde435ebbfeae580612", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e11d9e367325bbc109822e15fda04a9597e9e931c3f6fb954ecd5d0c6ac3018b", "generation_seconds_batch": 16.382089612074196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.48569655418396, "target_z": 2.187500134925847, "ce": 6.070269584655762, "genuineness": 4.469690799713135, "identity": 0.42309337854385376, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f4ddef43163bcd1946a449af3f92f9f00287d562cfc4ecde435ebbfeae580612.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "f4df437cd506dafde3414145bd9f51023c4f378a7bb0b465197e7278d854b5ec", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "193b65790d1a2bb1294c86fa4bb724ae8ba3512fac21ca34903e331aa74440d1", "generation_seconds_batch": 21.55313129001297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.334704875946045, "target_z": 1.9140626517915778, "ce": 6.356205940246582, "genuineness": 4.532451152801514, "identity": 0.4308760464191437, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f4df437cd506dafde3414145bd9f51023c4f378a7bb0b465197e7278d854b5ec.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "f4efd5fac901e95587a26c35df9ee1c59a41165b207cffff8f74708b5fd3ca10", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b668763ba67cf631accaaed2aea8acdcc3d36e47e6c3d76c6aff504c2b545be8", "generation_seconds_batch": 21.83590563701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6530851721763611, "target_z": 0.6796874966268538, "ce": 6.38797664642334, "genuineness": 4.293961524963379, "identity": 0.5103116035461426, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f4efd5fac901e95587a26c35df9ee1c59a41165b207cffff8f74708b5fd3ca10.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": "f50ea54dfdc82fd880ca94f56294228634e4dcc9c5b230181d43d37614118771", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Your message arrived after I had left.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a200c1cdf4c05051394343d2417d4d7d2539bf00267797065e191edcb9f4d7e4", "generation_seconds_batch": 14.430117215961218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1880271434783936, "target_z": 1.6484374831342692, "ce": 6.292664527893066, "genuineness": 4.093128204345703, "identity": 0.7098166346549988, "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_Astonishment_Surprise/f50ea54dfdc82fd880ca94f56294228634e4dcc9c5b230181d43d37614118771.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "f55d235fe3f8dfde7d0adb455493a0ecb8da03a0a28f9792cacdb6ccf7a35a08", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7e2bde2368aeec4b95303b9ada14839307b6781cd6ab5aeb3d03bc225cbf712a", "generation_seconds_batch": 16.446935564978048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.452902317047119, "target_z": 5.749999730148306, "ce": 5.911416053771973, "genuineness": 3.735394239425659, "identity": 0.6451997756958008, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f55d235fe3f8dfde7d0adb455493a0ecb8da03a0a28f9792cacdb6ccf7a35a08.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "f5c151aa29b556c0bd5a7aae7d21a227f996bef45be133457941e43a8c936625", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "361cc54ad2ad87cfa2dd801b2557fc821bfaf2cc098b6a1696b2adec0e661f09", "generation_seconds_batch": 17.94848587096203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4339278936386108, "target_z": 2.093749986507415, "ce": 6.141753673553467, "genuineness": 4.068024158477783, "identity": 0.684097409248352, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f5c151aa29b556c0bd5a7aae7d21a227f996bef45be133457941e43a8c936625.mp3" }, { "id": "emo_Astonishment_Surprise-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-0", "key": "f61631cf18720d56869b2ba37b7627c0076d7b3486eedfb3effa706cb9073d34", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La porte est encore ouverte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c1f78751069c9be70f2d052f07af98ed0bad0946ea13635800db21e8e1fedac4", "generation_seconds_batch": 21.259099671035074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3931637704372406, "target_z": 0.20898437752985963, "ce": 5.998785495758057, "genuineness": 4.444586753845215, "identity": 0.7633312940597534, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f61631cf18720d56869b2ba37b7627c0076d7b3486eedfb3effa706cb9073d34.mp3" }, { "id": "emo_Astonishment_Surprise-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-1", "key": "f6a8ee3a7177ec5e8eb193d32af08bd5ceb392252e925a8a92d98ab95b16e83c", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] I found the little box.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0a016cc362dbeefcff7e8ec569c90e44593d906680c4cc2e371c8ee79cc0d5bf", "generation_seconds_batch": 22.908519653021358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5719774961471558, "target_z": 2.343750094448093, "ce": 6.3641486167907715, "genuineness": 4.469690799713135, "identity": 0.46352237462997437, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f6a8ee3a7177ec5e8eb193d32af08bd5ceb392252e925a8a92d98ab95b16e83c.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "f6afaf673ef8cfff3b60488eb9d89df130bdaa6fdcd923655ff27bc8fccd907f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8e6ae0083b46c07633c38572ba120e762f62b9cdcad74c5c7bb2784a7e85df52", "generation_seconds_batch": 18.200750636984594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5538620948791504, "target_z": 0.5000000539703388, "ce": 6.435632705688477, "genuineness": 4.231201171875, "identity": 0.407211571931839, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f6afaf673ef8cfff3b60488eb9d89df130bdaa6fdcd923655ff27bc8fccd907f.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "73c4e6e63c386caedd34993798fdff06c5b9826400bdc3362e66e57930413294", "generation_seconds_batch": 16.572140228003263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24109357595443726, "target_z": -0.0664062381939884, "ce": 6.197352409362793, "genuineness": 4.419482707977295, "identity": 0.6574381589889526, "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_Astonishment_Surprise/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f7c13574d18fd9e265a81ea6d0322eb4e69b90837975ed4419450bb4d0144cd1", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9488ff965b7a3d033dafbadd88df51e5e21d1f078f0fccfd5fd81af0c53b0516", "generation_seconds_batch": 16.278709932928905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8135641813278198, "target_z": 2.7812500674629232, "ce": 6.141753673553467, "genuineness": 4.137060642242432, "identity": 0.6357474327087402, "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_Astonishment_Surprise/f7c13574d18fd9e265a81ea6d0322eb4e69b90837975ed4419450bb4d0144cd1.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_Astonishment_Surprise", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": "c6101a543dccb4ca8963a45f0ae603e6c78ce259a543d0dc3f9c7013cd303fcf", "generation_seconds_batch": 15.851573260035366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2707526385784149, "target_z": -0.012695334847093395, "ce": 6.316492557525635, "genuineness": 4.413206577301025, "identity": 0.6229867935180664, "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_Astonishment_Surprise/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "f886218857d4be037878eeed78b6c1b063346eef7a1066f723201e1b7805cb88", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7ddc070a07f21faf34c61e9807f88cea52861f703b5509e57885e1dd9b7f86dd", "generation_seconds_batch": 17.027932845056057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3519610166549683, "target_z": 1.9453125573434848, "ce": 6.109982967376709, "genuineness": 4.20609712600708, "identity": 0.6329232454299927, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f886218857d4be037878eeed78b6c1b063346eef7a1066f723201e1b7805cb88.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "f91736ffc456f8ce212c6f341a53533eb4fbbd806b8a65f79378b3164d341702", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b78928fc94baf8911243d51e0b8055315fa6c36acd3f7d04960f0b4d27d2fb4e", "generation_seconds_batch": 21.63060807203874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9861260652542114, "target_z": 3.093749986507415, "ce": 6.062326908111572, "genuineness": 4.080576419830322, "identity": 0.5744026899337769, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f91736ffc456f8ce212c6f341a53533eb4fbbd806b8a65f79378b3164d341702.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "f91f627183743ad0c7bfe4ddae6294dfbfcd8b81df593cd0b149e634cec75418", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3ab386aa552ae24533d568d978fea454da4dd495d67bfa44bcab1cf48befb183", "generation_seconds_batch": 23.361487068003044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.74539852142334, "target_z": 4.468749932537077, "ce": 6.165581703186035, "genuineness": 4.13078498840332, "identity": 0.5392056107521057, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/f91f627183743ad0c7bfe4ddae6294dfbfcd8b81df593cd0b149e634cec75418.mp3" }, { "id": "emo_Astonishment_Surprise-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-en-0", "key": "f98f7e1c975bd4572720f6ff293d41c062a311a66c827c712a7d1d414ac8df8f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] The door is still open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "03b8a29617f02181fd0bcbd192f871a12b5ceb0a11e24ebd8e6d7ce23b5e0629", "generation_seconds_batch": 22.080137225915678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2556534707546234, "target_z": -0.04003908316052031, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.37620770931243896, "hypothesis": "The 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_Astonishment_Surprise/f98f7e1c975bd4572720f6ff293d41c062a311a66c827c712a7d1d414ac8df8f.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "fa32862f0000e01894cba7b9e485b7b9e7357bc733359c4e4f30f0f273dbee17", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d470e692668525c78b49e922949b4c71cd84201be4776634b0a0a4165aa996ce", "generation_seconds_batch": 15.706191648030654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.136258602142334, "target_z": 1.5546875505971927, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.6004914045333862, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fa32862f0000e01894cba7b9e485b7b9e7357bc733359c4e4f30f0f273dbee17.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": "fa451f3d224671082341f7f0166a2ee0bd13275041e3bf375eb7e9e8bea8ce87", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19e33c606a7d8c05b14baf3314f6845d036b99cebacae80174204174d56a469a", "generation_seconds_batch": 16.24778040498495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8308203220367432, "target_z": 2.812499973014831, "ce": 6.070269584655762, "genuineness": 4.494794845581055, "identity": 0.6404911279678345, "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_Astonishment_Surprise/fa451f3d224671082341f7f0166a2ee0bd13275041e3bf375eb7e9e8bea8ce87.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "fa49bdc63292cdecd2ff380d068413f8ac4dd788573b9c8a12923d48a5205378", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3600fb47c15bd59e0e87aa287fcf5f7f8b5e1b5876212cb72aee4e653bc7c96c", "generation_seconds_batch": 23.05354540294502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.528836965560913, "target_z": 2.2656250067462924, "ce": 6.205295085906982, "genuineness": 4.168440818786621, "identity": 0.7021023035049438, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fa49bdc63292cdecd2ff380d068413f8ac4dd788573b9c8a12923d48a5205378.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": "fa97c2e3e3df78bf5a6b902500140c3bc8d1c2669c78771ab8b0d483cf7c0959", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85f607b68924ec0766c8e7a709e254d16a9f0026c8501609128c65422e68ad7d", "generation_seconds_batch": 14.56160689110402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4175307750701904, "target_z": 3.874999784118645, "ce": 6.1020402908325195, "genuineness": 4.174716949462891, "identity": 0.6637006998062134, "hypothesis": "Quelqu'un déplaçait la petite chaise bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fa97c2e3e3df78bf5a6b902500140c3bc8d1c2669c78771ab8b0d483cf7c0959.mp3" }, { "id": "emo_Astonishment_Surprise-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-1", "key": "fadf85cae5bbb37e55d333184c68db778195e6dee4196386ef3fa6fdc8c1eb01", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "13f62c04f2cc807d2123958f56c65fd987b742b1da861dd4947f79c1d1ab5045", "generation_seconds_batch": 19.461320857983083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1923412084579468, "target_z": 1.6562500134925846, "ce": 6.213237762451172, "genuineness": 4.306513786315918, "identity": 0.6530929803848267, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fadf85cae5bbb37e55d333184c68db778195e6dee4196386ef3fa6fdc8c1eb01.mp3" }, { "id": "emo_Astonishment_Surprise-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-1", "key": "fafb55b4326225c248a8b3432e407a8ebabc7a8f7bfeb07aa39213bbe2f3239f", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "50f3b3525c1fa5a1ef96e62228a950e2894e058ae1c651abef3a5094d57976a2", "generation_seconds_batch": 22.62009094201494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8567047119140625, "target_z": 2.8593751551647237, "ce": 6.23706579208374, "genuineness": 4.13078498840332, "identity": 0.38831862807273865, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fafb55b4326225c248a8b3432e407a8ebabc7a8f7bfeb07aa39213bbe2f3239f.mp3" }, { "id": "emo_Astonishment_Surprise-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-es-1", "key": "fb70b26febf0295d285327bdd17b8628603385bfd4d840755f0065f7e9a8e096", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] He encontrado la cajita.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2510da5072bcbf5209d80ae709ef3b02927f6ade10627cf583020d96fd5bbcf1", "generation_seconds_batch": 21.694813712034374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.364903211593628, "target_z": 1.9687501484184315, "ce": 6.062326908111572, "genuineness": 4.15588903427124, "identity": 0.23693251609802246, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fb70b26febf0295d285327bdd17b8628603385bfd4d840755f0065f7e9a8e096.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": "fbbc84c43db1cd4819b684f28284ff72b8e5a569d917bb9a735614bdfb3608ee", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1cb11c8407c25b85ff1cdd33b66c2328f11db9d504e27ae8112562f2cd7fca9f", "generation_seconds_batch": 16.278709932928905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1405726671218872, "target_z": 1.562500080955508, "ce": 6.141753673553467, "genuineness": 4.356721878051758, "identity": 0.7033559083938599, "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_Astonishment_Surprise/fbbc84c43db1cd4819b684f28284ff72b8e5a569d917bb9a735614bdfb3608ee.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": "fce5773a498ed4b015263427bd51e1bf8145a23fa08ad3700a78f0dc693999f4", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1636dd7ebf6c7d5718722183c5b8b952dc62b9cd6f6c4ec8609b749cb57b6e88", "generation_seconds_batch": 24.276902699028142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6418612003326416, "target_z": 4.281249635700213, "ce": 6.24500846862793, "genuineness": 4.218649387359619, "identity": 0.7175909280776978, "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_Astonishment_Surprise/fce5773a498ed4b015263427bd51e1bf8145a23fa08ad3700a78f0dc693999f4.mp3" }, { "id": "emo_Astonishment_Surprise-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-de-0", "key": "fde1099e53a76aff3b0f8a523e2db6544d3a7cb156705bc95c0045123799f4ce", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "82a21321fd6867f3e687d3aa920b17825d630c4305a3bc770b34d7ff4eaf1ac6", "generation_seconds_batch": 22.99911767593585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3467877507209778, "target_z": 0.125, "ce": 6.403861999511719, "genuineness": 4.457139015197754, "identity": 0.6859990358352661, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fde1099e53a76aff3b0f8a523e2db6544d3a7cb156705bc95c0045123799f4ce.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "fe28eb091a65fb104575b05328c60d717bedd091090ade75678686d0a571ddd4", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ae5b73f140ae68aafb985311ba87eaaedf1734da858749c31a09c549de6e25e0", "generation_seconds_batch": 23.456347284954973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5029526948928833, "target_z": 2.218750040477754, "ce": 6.125868320465088, "genuineness": 4.074300289154053, "identity": 0.7082172632217407, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fe28eb091a65fb104575b05328c60d717bedd091090ade75678686d0a571ddd4.mp3" }, { "id": "emo_Astonishment_Surprise-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-nl-0", "key": "fe583190c5e6e58e97b928c294edc48aab29699e970ac88a00b1f75348be5e9a", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] De deur staat nog open.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b03cf750ab09434f2190216521ff95baec1f585a93437c177ef8a844940c24bd", "generation_seconds_batch": 25.65894447104074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4347870349884033, "target_z": 3.906249905551907, "ce": 5.935244083404541, "genuineness": 3.8797430992126465, "identity": 0.09183625876903534, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fe583190c5e6e58e97b928c294edc48aab29699e970ac88a00b1f75348be5e9a.mp3" }, { "id": "emo_Astonishment_Surprise-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Astonishment_Surprise-fr-1", "key": "fe7503fe0d0b2075f16b7e3b587a16490a00d3fb200c9a4a2a9be0cf558ea13e", "bucket": "emo_Astonishment_Surprise", "phase": "grid", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1174b86dc02c02d5edc8c6348470a81964f2ee6760404a2a9b0c4340b27a2a69", "generation_seconds_batch": 19.531220534001477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4665026068687439, "target_z": 0.3417969078881752, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6955511569976807, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Astonishment_Surprise/fe7503fe0d0b2075f16b7e3b587a16490a00d3fb200c9a4a2a9be0cf558ea13e.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": "ff3c24cb1c939492493870973ccdc0bc2604eee190c1e290188c3ddfcc98ae85", "bucket": "emo_Astonishment_Surprise", "phase": "heldout", "candidate": "manual-bedaa97ab879", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Target resonance shift; the surprise should sound as if the vocal tract has momentarily widened or constricted drastically, changing the perceived timbre.\nSCRIPT:\n(Deliver the opening with a tightly focused, forward placement in the mouth, low in resonance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Immediately shift the resonance upward and backward, creating a sudden, bright, almost metallic quality of surprise.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation carry that heightened, bright resonance, sustaining the unusual timbre until the very end.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c84a1186252c6471f2b4bb3fd00f5b564daf879ead9d694236dfe13f01538329", "generation_seconds_batch": 23.6722528799437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.48569655418396, "target_z": 2.187500134925847, "ce": 6.141753673553467, "genuineness": 4.369274139404297, "identity": 0.7011996507644653, "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_Astonishment_Surprise/ff3c24cb1c939492493870973ccdc0bc2604eee190c1e290188c3ddfcc98ae85.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "62d4859f7ab9d8ae30902ef552e3a138cc36d2401184951886445476fda449ef", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.34463071823120117, "target_z": 0.12109373482084222, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.43600285053253174, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/a76348887e68b6ef697b370b.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "6055d17e3757ff5701dd8d5ad6920b4d75092a0614441746a2895ddbe5713bf1", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.06421759724617004, "target_z": -0.3867187415671346, "ce": 6.372091293334961, "genuineness": 4.545003414154053, "identity": 0.45118293166160583, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/39686840ba2f38de692694bf.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "46da46263958cdbcea90f61f804c2a2534ae5c24a3e3f867f12b8950f558ef01", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.07500271499156952, "target_z": -0.36718749662685385, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.4031792879104614, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/12602df204a3e7497ea2ba13.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "4bb3275e03a7b6a30246545c693d8baa8eb74e89bb45b3cefe19f6f4c51d7a76", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.12245723605155945, "target_z": -0.2812500134925847, "ce": 6.1020402908325195, "genuineness": 4.7834930419921875, "identity": 0.4909714162349701, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/ccfe5dc59ca3a05aa2f53fc0.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "c7d856eb11c5c522b33025a224aa28fdd3ff668aa0412756364126cc9786894b", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.17476508021354675, "target_z": -0.18652343370521055, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.6297396421432495, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/96f71d5591306b445cef369e.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "1328a0b3d81faea96dd35cbab32a99a998aba127d913559c2f239a6b4ef71dd3", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.05235396325588226, "target_z": -0.4082031190969942, "ce": 6.24500846862793, "genuineness": 4.469690799713135, "identity": 0.7791318297386169, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/7b4e4c3c86c6ac15ae75d772.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "5d889099c757d5af4715129d2d1aa412105c7483cb628db989e5bc02ccbf5c25", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.06961014866828918, "target_z": -0.3769531325895789, "ce": 6.173524379730225, "genuineness": 4.7081804275512695, "identity": 0.5580114722251892, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/71b67ec71d0384f4abc3dcfc.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-0-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "744b4cc2fb61eb1b15bad348af90792cf9218be4c136e96df4a8a2a6db49db7f", "task_id": "emo_Astonishment_Surprise-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.085787832736969, "target_z": -0.3476562516865731, "ce": 6.23706579208374, "genuineness": 4.1998209953308105, "identity": 0.257805198431015, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/fe2d7fa4e59f55344586f278.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "8660d6a72a3a4f2053322cf4c713f4d840c2fa38136df8661cbd4c1ae7b1d674", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.15049855411052704, "target_z": -0.23046875505971925, "ce": 6.38003396987915, "genuineness": 4.356721878051758, "identity": 0.4884917438030243, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/45f1731e28b081bff2b95fba.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "14ecabea01e89489279ffba4aa61a7a5557d4caf3c61c30fbe1390c35b83e427", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.15373408794403076, "target_z": -0.22460938427615199, "ce": 6.3641486167907715, "genuineness": 4.293961524963379, "identity": 0.3448958396911621, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/155bb39b309b2cf97e1d9634.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "5d0aba7c582ed21c831f043fc3372ec0ea0ed2acf1642cdc3c9039b7d7c5b361", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 1.304506540298462, "target_z": 1.859375155164724, "ce": 6.419747352600098, "genuineness": 4.356721878051758, "identity": 0.6551851034164429, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/9210a2feb557970f0f92dce7.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "a1b72859be0ae26768991b15740c058c4ced1e05114ca93f2e4c0f96922697a1", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.42767614126205444, "target_z": 0.2714843505446902, "ce": 6.403861999511719, "genuineness": 4.582659721374512, "identity": 0.5122951865196228, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/7535a626fc95c8e58c2460f2.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "3faa2072d5099923801336bb973f5bd35b1c2e592b91321c29b665ecf9501516", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.25619274377822876, "target_z": -0.039062489880561484, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.3260449767112732, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/a51e768d35cd997a97323536.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "40f798e7df767caccdd7c242c72fd7ead238c73526556afba726c28bd6fb9a31", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.22114109992980957, "target_z": -0.10253905617535093, "ce": 6.3641486167907715, "genuineness": 4.18099308013916, "identity": 0.35881850123405457, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/ce950bc445ea20d11d39b4da.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "9c61f82460c14c0906321a33533b3f5095a0d650d4bd5d67d5cfd7bfefe599c5", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.26212456822395325, "target_z": -0.028320287623046975, "ce": 6.3641486167907715, "genuineness": 4.174716949462891, "identity": 0.5041251182556152, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/2f84051468a5d1261cc8a4a0.mp3" }, { "key": "original-emo_Astonishment_Surprise-de-1-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "2937a22c6ac8a7436ae6c5dfc643ae90e2c4c39600d0817c15cb78c20824d676", "task_id": "emo_Astonishment_Surprise-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.22168034315109253, "target_z": -0.10156251686573087, "ce": 6.523001670837402, "genuineness": 4.482243061065674, "identity": 0.4951741099357605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/de/eba70ab53dcd0d2d311349c0.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "70b7ac8d491c85d9e5a2375fb734c7c90fa6fb106faa916d17646e900fd6a108", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.20658117532730103, "target_z": -0.12890626517915776, "ce": 6.205295085906982, "genuineness": 4.080576419830322, "identity": 0.3274010419845581, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/8952feb7d37ac231dd402390.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "e60268502e8df883c68b26e4445ab99da983fa6de0dc3e8d0dd00f47e4147cf6", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.04696139693260193, "target_z": -0.41796875505971925, "ce": 6.340320587158203, "genuineness": 4.068024158477783, "identity": 0.37310248613357544, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/1628f7a835d500277f188586.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "6065c3dc2e841d1450838816f3981bbfad86ffdc7af09c536de00af347e7e2f9", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.17746135592460632, "target_z": -0.1816406292164327, "ce": 6.23706579208374, "genuineness": 3.9048471450805664, "identity": 0.3113265633583069, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/413eedd8b4de83622ddddea6.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "f9982f42a278e52565fbe21be0fb837f64d9e8e2af91e854bcece7722d0aa54f", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.07500271499156952, "target_z": -0.36718749662685385, "ce": 6.2767791748046875, "genuineness": 4.061748504638672, "identity": 0.5321527719497681, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/ac54d7880b3fe25c51ff2f03.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "2854da8feeaa14caeb1d7ebd8a264016f9912ac4e51f9155c6d03037dff57754", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.057746514678001404, "target_z": -0.3984375101194385, "ce": 6.1894097328186035, "genuineness": 4.055472373962402, "identity": 0.2533079981803894, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/8b09a133e6405f6fa6cc3948.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "984da69ae38a837cc2b5903418f7d2bd546fcc50ae222d3d06b9559d606cdfde", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.18878573179244995, "target_z": -0.16113281798136253, "ce": 6.022613525390625, "genuineness": 3.8671910762786865, "identity": 0.49804335832595825, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/ab5f2c40f80a5460fcd3cab8.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "d0c5e5cc1be0c35e1fa0e51fe6c2e4db13782e7143f7c238f83ced2b4ea4861c", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.17368656396865845, "target_z": -0.18847656629478945, "ce": 6.157639026641846, "genuineness": 3.785602569580078, "identity": 0.3116435706615448, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/c353ae67529ac58d2e1a29a9.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-0-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "60602459cf173118ba05bd644e9a882005fc76eeba6eb747dea087e2238a7c8a", "task_id": "emo_Astonishment_Surprise-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.0426473468542099, "target_z": -0.4257812584328654, "ce": 6.23706579208374, "genuineness": 3.9048471450805664, "identity": 0.37956511974334717, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/2e9a61d86bf6072b3c3c2741.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "0c810f8da0c1eea8c0e9ccb1fbcc01d126fc813459d986803588642cb6e3f83d", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5633493661880493, "target_z": 2.3281250337314616, "ce": 6.3641486167907715, "genuineness": 4.256305694580078, "identity": 0.443114697933197, "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_Astonishment_Surprise/en/80754d1b53ab8431543845d1.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "c63e92755d4e88b6113c8a89c3e7d5e1edf9545b0e5dc71db4fb286286da65d3", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4511841535568237, "target_z": 2.1250001079406777, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.23111002147197723, "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_Astonishment_Surprise/en/f7ebac2125fcf7976d098da4.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "5a8621d75b9c3496a6f192a965818bbd049ad7cef09895502c3d38e2a0b67fa9", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6841427087783813, "target_z": 2.5468750202388772, "ce": 6.300607204437256, "genuineness": 4.400654315948486, "identity": 0.3478330671787262, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/7a1c5b973d78885f750177ab.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "fc7c3900a9860f7044d0881de03dfcc8491289a5ab31e8a01ad54779990781d6", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.287250280380249, "target_z": 1.8281250337314616, "ce": 6.38797664642334, "genuineness": 4.369274139404297, "identity": 0.5461620092391968, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/8e3becfc681607abbdd8ea76.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "072e297446f9cc9b5038281aac75c7513106d882a168ab993c8bdeca09715024", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0413495302200317, "target_z": 1.3828125303583156, "ce": 6.435632705688477, "genuineness": 4.444586753845215, "identity": 0.3484713137149811, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/9db1f2c9c16723159a92e387.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "7aec21694eed38862389386c7ccc952be1d9608a1c8720e389cc93569d781c4c", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.9291843175888062, "target_z": 1.1796876045675313, "ce": 6.419747352600098, "genuineness": 4.406930446624756, "identity": 0.40536201000213623, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/10b9178444027a2e2a807f92.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "6534349656f725584c2817482fd0611e4df7198b4ba0f4030001168cc5382677", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.735911250114441, "target_z": 2.6406249527759535, "ce": 6.292664527893066, "genuineness": 4.231201171875, "identity": 0.41811662912368774, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/209cd4300c36fe793a3b1c9e.mp3" }, { "key": "original-emo_Astonishment_Surprise-en-1-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "8d306139533e0e6dc160920ce19eaf0b134ec6a94547878c9f4a6a4b77b0831b", "task_id": "emo_Astonishment_Surprise-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0931180715560913, "target_z": 1.4765624628953922, "ce": 6.372091293334961, "genuineness": 4.381826400756836, "identity": 0.2824651300907135, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/en/9dbdff72c773fe8fbc3006f8.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "f957f4029d5502b624d1721ec75f6c1fe5f675143728223951564fd915819610", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.10304403305053711, "target_z": -0.3164062381939884, "ce": 6.070269584655762, "genuineness": 4.18099308013916, "identity": 0.6912592649459839, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/c6db3841d6bb241789e13923.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "cd62026fbbd7e1401c36546ee53703599b78ea27485bc32373f8d0726ece00bc", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.04049032926559448, "target_z": -0.42968749662685385, "ce": 6.173524379730225, "genuineness": 4.124508857727051, "identity": 0.5283663868904114, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/b5cbf15f0b6ece0543149899.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "9f6190d0f0bbcf2f3e1613c54c78143b6de018286f4d7579cec20374843e4335", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.1823146641254425, "target_z": -0.1728515595484971, "ce": 6.2767791748046875, "genuineness": 4.400654315948486, "identity": 0.48265892267227173, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/1f80c9eccc9d7dab5985bb0b.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "7c33c7914a7b4f61e8571257d3e0adf1260b4cb8167036327658b0d2e8fd05f8", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.4546389579772949, "target_z": 0.32031250337314615, "ce": 6.181467056274414, "genuineness": 4.243753433227539, "identity": 0.5315797924995422, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/926060cfc712ec77f96034d7.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "efe03f19fcaaaa10ab13e13072011f3e14010a20f0842316d5a7f2494b056b9e", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.09549444913864136, "target_z": -0.33007811235070184, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.5148345232009888, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/40f687a149d51183a8e81e96.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "4623a410be1d5438501936abb9df9af3509beb77659b628e884656752ced42a2", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.6638703346252441, "target_z": 0.6992188225226427, "ce": 5.974957466125488, "genuineness": 4.080576419830322, "identity": 0.2970897853374481, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/8049dbe2f8c7899219d036cf.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "1584778fd4995fde2cec89e388371680c7c7ca6c3a808f9a87751e13a0941d33", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.29232290387153625, "target_z": 0.026367209003806853, "ce": 6.022613525390625, "genuineness": 3.9299514293670654, "identity": 0.4524552524089813, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/392650a271253e6cebbea0d7.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-0-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "0558f955ffcd066edaa6d46c1f624d85692fca5f190852cf87cfc775ab040c27", "task_id": "emo_Astonishment_Surprise-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.23192621767520905, "target_z": -0.08300781123507019, "ce": 5.895530700683594, "genuineness": 3.8420867919921875, "identity": 0.37246474623680115, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/4e0db434cf9c03a18155bf14.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "ad06a5ef1158736db1e410400677dacd340878eed06e8531bcb487f187e2b09a", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.7221099138259888, "target_z": 0.804687442656515, "ce": 6.213237762451172, "genuineness": 4.545003414154053, "identity": 0.6011430025100708, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/d99455c436ef5e06e90047fe.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "9938c28592501b7726b323ee79b76aea346ee2ab73899c323590708fb2fdb348", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.6530851721763611, "target_z": 0.6796874966268538, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.5038855671882629, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/04209b88b28150f91c99bfc1.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "d91952d3dcd24c16de92c28525ca1b3522437605bfa5ee8f5507438d5d18660b", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2743080854415894, "target_z": 1.8046874426565152, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.5039654970169067, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/06ffbee8f2df959ba359f977.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "e4bba11ba1dc735097c1ecbe4ece0c67e6b2237ef333ae7102b5ec14dfd81c3f", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.7652504444122314, "target_z": 0.8828125303583155, "ce": 6.054384231567383, "genuineness": 4.331617832183838, "identity": 0.4608355164527893, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/c475a0d1df4ce1eef48fbd6e.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "20cc8f3099355891b0008e873b9ff61bab58fdd0bc0b1d964c66301bc9f5479f", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.40880221128463745, "target_z": 0.23730471912324538, "ce": 6.260893821716309, "genuineness": 4.796044826507568, "identity": 0.5333634614944458, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/82d958923aad6bc9c722389d.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "2fe49eb16314fb97a7b28fca3635bb15fec3e3b20a852aae9592ab340f656665", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.7846636772155762, "target_z": 0.9179688090300581, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.5768319964408875, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/6be599bb3d41e60b39089d48.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "2838358693d74db74bdee01da1b340a711d26e68f1fc78ac269ce3c9dcae08b5", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.6595562696456909, "target_z": 0.6914062921643271, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.5902408957481384, "hypothesis": "He encontrado la cajita que estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/36805237f129dd58216b1ca1.mp3" }, { "key": "original-emo_Astonishment_Surprise-es-1-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "f9727f901a76b66759b6ca613c43599f15de9feb8bf4b82d524ddbfa60b46683", "task_id": "emo_Astonishment_Surprise-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.057746514678001404, "target_z": -0.3984375101194385, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.47108954191207886, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/es/8645e6755fb453c773c7a748.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "a50120fd5799eed595c7dba562a73619094ca0da2890934f64670464da85c5a1", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.02539116144180298, "target_z": -0.45703124494028075, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.5610095262527466, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/abba5370b6e43902bba44cf4.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "775cd5f67ffac010023e13ffb54606c59ae88eae5c7b7cd0ff78e7c81c6a5f52", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.001663893461227417, "target_z": -0.5, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.4422135055065155, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/609299a1657948b89b104224.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "c6e595d60b48f9a76631bf5a83b135c7986d5125fc491c09964cfc5370ac2053", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.03833329677581787, "target_z": -0.4335937618060116, "ce": 6.109982967376709, "genuineness": 4.143336772918701, "identity": 0.6271266937255859, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/baf695bf40bdeee86008c92f.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "e341f7a9689e774f84f6c9defe471426babce8415a87d567d796476a43613541", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.16074442863464355, "target_z": -0.2119140494290586, "ce": 5.998785495758057, "genuineness": 4.375550270080566, "identity": 0.7138535976409912, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/45d11952106bef42286b0da7.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "809ea3bdb4485b13c06f24ab661fd0c498f907587e5170a0b311ccfbf33eeb09", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": -0.0004931390285491943, "target_z": -0.5039062651791578, "ce": 6.260893821716309, "genuineness": 4.432034492492676, "identity": 0.7700908184051514, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/ed6d26c5047e16fda03cee3f.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "ffd0626bd56d91d22eedce98faa8f4a565119d75bfb8307e6d93d7077c587fd2", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.0286266952753067, "target_z": -0.45117187415671345, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.3956650495529175, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/fff42bb50997caa02069fc3d.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "3de6cbb28c98ecd35b1b8eb1da3ab627b7bd6364e5f23703c8213f021e6280a8", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.06853164732456207, "target_z": -0.3789062381939884, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.7024581432342529, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/9b900e8edc395dcfacbfd22e.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-0-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "c52787ec709baefa328f5cc26354f2b1ee8683ffd977e6f2f8b80ca5ef470ec9", "task_id": "emo_Astonishment_Surprise-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.22060184180736542, "target_z": -0.10351562247014037, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.6540806889533997, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/49c5029443020718ee69ba66.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "0343981f62e7616e9c367bc6c936f7142c442061bc41becfd856e9d38b03d71c", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.248643159866333, "target_z": -0.05273436403727494, "ce": 6.054384231567383, "genuineness": 4.607763767242432, "identity": 0.6423047184944153, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/74c080882d0a8c2ada57a98d.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "76310d3a77c894bd3e26864d39136019fdc53987492016a7903155bd7c61ca72", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.07500271499156952, "target_z": -0.36718749662685385, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.636617124080658, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/c569fcad2ea69498b86413e8.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "9d6916963991417a0d4beb20dbb120114daa11294c8a2973701d40c0b37977fb", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.521506667137146, "target_z": 0.44140618422364963, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.8135759830474854, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/6de503c75fe6ecc0198fa95f.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "8c9af79b5c386770c92649458690b67d730a9255600b43d2e8bd0111363e02d3", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.0286266952753067, "target_z": -0.45117187415671345, "ce": 6.284721851348877, "genuineness": 4.519899368286133, "identity": 0.7032935619354248, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/74b2152f366fdd17715349d9.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "7ea727b24265a5f926daac6575a79613b18988a8dec1bc9157a216c3f71caf38", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.01460602879524231, "target_z": -0.47656251686573087, "ce": 5.959072113037109, "genuineness": 4.65797233581543, "identity": 0.6956436038017273, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/2db6d73003ba4bd54504bdad.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "b8be89a2a74951492dd8c15d5f51cb883415efbc60a153ec754c44712ba8f785", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.0426473468542099, "target_z": -0.4257812584328654, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.6677941083908081, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/14cde411ab2ef2b0311f0228.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "484c248a4d35d62448194625599aeeecc32b6d6595606c3d0f1ac3534f73873e", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": -0.015592306852340698, "target_z": -0.5312500134925847, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.7502416968345642, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/4f5410e48bfa0346f64a006d.mp3" }, { "key": "original-emo_Astonishment_Surprise-fr-1-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "58c438c325f9b0a3d52406a2e23a528c6a26401bb0c405acdbc9e06eb5e474ea", "task_id": "emo_Astonishment_Surprise-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.7393661737442017, "target_z": 0.8359375640897773, "ce": 5.5539960861206055, "genuineness": 4.1998209953308105, "identity": 0.7435159087181091, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/fr/79176d98b4a8c24e0f690ced.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "dd39387b3150d2e8053c77dc5a9f036752b30ee1b9f21ded3c775d271cca07d9", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.8127049207687378, "target_z": 0.9687499325370765, "ce": 6.006728172302246, "genuineness": 4.118232727050781, "identity": 0.681288480758667, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/43a569c282cb20f40a22f572.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "c9e67e153ec45ce7eb142216b50f552c57fb47bea48a690e7d11a77ba973c2d0", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 1.1750850677490234, "target_z": 1.6250001079406775, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.32520538568496704, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/24716fd769ba942290657112.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "52556bc9e54565226162b7dc2f55b1eb0f6adfca0294ff18e9a3afaa8f30c78e", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.6142587661743164, "target_z": 0.6093750472240465, "ce": 6.0146708488464355, "genuineness": 4.093128204345703, "identity": 0.7437546849250793, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/fe34850970483e8f925406e7.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "1c3fbf9ac4014965ef2ec8e342fff57086428bc522d9dde8754046191d593b20", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.6638703346252441, "target_z": 0.6992188225226427, "ce": 6.149696350097656, "genuineness": 4.174716949462891, "identity": 0.6248459815979004, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/b84d2a2f89c552c57afd7645.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "fca4b244d39ba051827655330f22d5adb09bb076169fe7028cf003f9d8a87c2b", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.503171980381012, "target_z": 0.4082030921118248, "ce": 6.229123115539551, "genuineness": 4.306513786315918, "identity": 0.7092361450195312, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/dea2aa9d5e860950357d1057.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "11256a869cd8747409008010b587c0372ffa741fecdf6e60965828d1faa43ce3", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.3721327781677246, "target_z": 0.17089842695891821, "ce": 6.1894097328186035, "genuineness": 4.319066047668457, "identity": 0.8011622428894043, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/c7dabcfa4fa64c660eb49756.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "77107d275aa7fc4eb4d2b85d26bc7ee8d32d6e6c5d7b50c22ccc88f670d7d830", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.324408620595932, "target_z": 0.08447264718466967, "ce": 6.308549880981445, "genuineness": 4.582659721374512, "identity": 0.7649185657501221, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/5db12cb68f9b27ae47734a92.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-0-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "f7dbc561be7b964fa5936dc4e532a0a6d7024d46cdf4e6f27671f4c1b16a18c5", "task_id": "emo_Astonishment_Surprise-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.5301347970962524, "target_z": 0.45703124494028075, "ce": 6.078212261199951, "genuineness": 4.432034492492676, "identity": 0.30437561869621277, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/38a7c5fb2c9b9b5d5c808416.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1701-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "333c9ccaee69ef349b34f5f3d95e9dc04a377572304aa6af90ebe5cc9b35a6f8", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.10735806822776794, "target_z": -0.3085937618060116, "ce": 6.157639026641846, "genuineness": 4.250029563903809, "identity": 0.6903614401817322, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/291bc254a84ba75276165863.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1701-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "78712abed1622270bb67496c88f1e20120b72f815843668365786418e131c0b0", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.32144272327423096, "target_z": 0.07910157304108179, "ce": 6.165581703186035, "genuineness": 4.149612903594971, "identity": 0.646752119064331, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/e5b2d5f6e60af785832fe826.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1701-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "a27b9b8be4163ffb336117e0db0f061f55557f7b80625626b2a14ec1bc948af4", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.7048537731170654, "target_z": 0.7734375371046079, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.680953860282898, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/a323c5c6565c806d83f43742.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1701-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "8a3a23ff9d21e60daa68daf985d2d4a760816ac3cf59da4aa2ee050c6c21b10e", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.5948455333709717, "target_z": 0.5742187685523039, "ce": 6.1020402908325195, "genuineness": 4.3504462242126465, "identity": 0.6103836894035339, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/f5018271e410ebfc0054364e.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1702-scale0.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "9a5d1ea767a633020cecf412813d5c7a6c984be52f78fdb22ed6bd4152326f51", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.08363081514835358, "target_z": -0.3515624898805615, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.6592133045196533, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/2ac34961e9c442aa6f50f72a.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1702-scale0.5", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "0e9506e7b1aba48b70133b1caafdb95a86084dc67c12c3c4445910a7d8231a2f", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.5581761002540588, "target_z": 0.5078124763879768, "ce": 6.165581703186035, "genuineness": 4.2751336097717285, "identity": 0.7461775541305542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/00c2ad05325e56230e821d7c.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1702-scale0.75", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "d3da7143d537d92d305b29c82fbf2a6f6b3e81106a90c7ad1a8716174821cfaa", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.9248702526092529, "target_z": 1.1718750742092159, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.6505985260009766, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/af5e1302d520911ad2f12c00.mp3" }, { "key": "original-emo_Astonishment_Surprise-nl-1-seed1702-scale1.0", "bucket": "emo_Astonishment_Surprise", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "576b851276defa6e10150b9be17959d1cd85510990ee4bcbe5df0c12ef97fdc2", "mp3_sha256": "a76165fad151c61e93ec329c31ebad4555e2ed25fb1c7b36d36895b3e42204d8", "task_id": "emo_Astonishment_Surprise-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Astonishment Surprise. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Astonishment Surprise. 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 Astonishment Surprise. 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 Astonishment Surprise. 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": 0.14672376215457916, "target_z": -0.23730469213807598, "ce": 6.09409761428833, "genuineness": 4.093128204345703, "identity": 0.5565587282180786, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Astonishment_Surprise/nl/3c7ed1a714ac2794b4a03216.mp3" } ], "source_standard_audio_unchanged": true }