{ "created_at": "2026-09-15T14:50:59+03:00", "status": "completed", "instance_id": 50735875, "gpu": "NVIDIA A100-SXM4-40GB", "dataset": "Seed-TTS-Eval English", "samples_per_model": 1088, "models": 33, "scored_audio": 35904, "completed_shards": 198, "dataset_sha256": "8a9386efb1768a90ffba66f8931e3887b53e9c9d1bf246eb46a8cce32bc7b1c1", "suite_sha256": "1a37627704da3f0158d29a0cc3cff712494dadd0f03553fea2511a01d60ea8a9", "source_commit": "3ce0a0aa9cf3c9b24d8e4d6c3d0315b7bf7adc0a", "asr": { "checkpoint": "Systran/faster-whisper-large-v3", "revision": "edaa852ec7e145841d8ffdb056a99866b5f0a478", "device": "cuda", "compute_type": "float16", "language": "en", "beam_size": 5, "temperature": 0, "condition_on_previous_text": false, "vad_filter": false }, "normalization": "whisper_english", "seed": 42, "repeats": 1, "ci_method": "95% prompt-cluster bootstrap; 1000 resamples; RNG seed 42; full 1088 prompts", "protocol": "Fixed provider voice/reference intelligibility; not official zero-shot speaker identity/SIM evaluation", "backup_verified_at": "2026-09-15T11:48:02.499471+00:00", "records": [ { "model": "kokoro", "name": "Kokoro", "checkpoint": "hexgrad/Kokoro-82M", "revision": "cbc78411372edb46f7e42030b241834a55fe0cb6", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.08802692033350468, "latency_p95_s": 0.10426744297146796, "rtf": 0.018666759712283744, "peak_vram_mib": 478.27685546875, "audio_seconds": 4623.275, "clipping_ratio": 0.0, "silence_ratio": 0.3701472327051314, "rms_dbfs": -26.425495242960476, "normalization_id": "whisper_english", "wer": 0.009629071422590639, "cer": 0.0024400404689638756, "mer": 0.00962423633776885, "wil": 0.01742962890275368, "wip": 0.9825703710972463, "word_hits": 11834, "word_substitutions": 94, "word_deletions": 15, "word_insertions": 6, "reference_words": 11943, "char_hits": 67093, "char_substitutions": 53, "char_deletions": 66, "char_insertions": 45, "reference_chars": 67212, "exact_match_rate": 0.9136029411764706, "raw": { "wer": 0.052422086720867206, "cer": 0.01234299936331539, "mer": 0.05240877148420964, "wil": 0.09932624372940968, "wip": 0.9006737562705903, "word_hits": 11192, "word_substitutions": 583, "word_deletions": 33, "word_insertions": 3, "reference_words": 11808, "char_hits": 68408, "char_substitutions": 359, "char_deletions": 341, "char_insertions": 153, "reference_chars": 69108, "exact_match_rate": 0.6507352941176471 }, "orthographic": { "wer": 0.012187896741430384, "cer": 0.00459090436358774, "mer": 0.012185833968012186, "wil": 0.022734798398738487, "wip": 0.9772652016012615, "word_hits": 11673, "word_substitutions": 126, "word_deletions": 16, "word_insertions": 2, "reference_words": 11815, "char_hits": 67032, "char_substitutions": 90, "char_deletions": 185, "char_insertions": 34, "reference_chars": 67307, "exact_match_rate": 0.890625 }, "wer_ci95": [ 0.007682849762477258, 0.011640828342247611 ], "cer_ci95": [ 0.001896678239861543, 0.0029770741117294947 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.009629071422590639, "cer": 0.0024400404689638756, "mer": 0.00962423633776885, "wil": 0.01742962890275368, "wip": 0.9825703710972463, "word_hits": 11834, "word_substitutions": 94, "word_deletions": 15, "word_insertions": 6, "reference_words": 11943, "char_hits": 67093, "char_substitutions": 53, "char_deletions": 66, "char_insertions": 45, "reference_chars": 67212, "exact_match_rate": 0.9136029411764706 } }, "utterance_mean_wer": 0.009572094061983769, "utterance_mean_cer": 0.002414540728261279 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-kokoro-seedtts_en-000", "result_sha256": "e4374dd51efe49586ae2b2117bd79bf8b9a6a40608a9ecb5b93ecea53c417303", "config_sha256": "5cec1b8a99c55408bdf9f8a7c5e8ef92b0ce8a01687d6bd038dbbcc0f30c442f", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-kokoro-seedtts_en-001", "result_sha256": "2089f0b7800f032b50978eb7b2872011150e283a45c77a4e6fe76d3f36607417", "config_sha256": "76ed25fe3a1a9cbf28420041887104f19d7d08ac6afb01275414e4edea97c0ba", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-kokoro-seedtts_en-002", "result_sha256": "b203730141545e95ea9762cc8211fdc442ff33cb2871f406bb6978ee100de8be", "config_sha256": "40ea26115c7a042d4cba93fad92beb6f7cddfba50871b63e2b52ec1e8eb530be", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-kokoro-seedtts_en-003", "result_sha256": "ce85fdf2a06c364706a9c28ed22eaeb20879a50860981a655b15c4ee6fad640b", "config_sha256": "553d429d96252d9b969aa2c16212bb5cf7faf3bd5b94f8f510a5a36778ba5b13", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-kokoro-seedtts_en-004", "result_sha256": "b684f833f86179df27649e89370ff5eeccdbb2c46a60cc3789154d3cc38e603b", "config_sha256": "58e3a03c6a02c9173fbfdfc804bb7a887ffc7e80a05932c73b00567acd493356", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-kokoro-seedtts_en-005", "result_sha256": "c093baeca1687ea5833f5f72c28da5f281e1d18e9624b2edbdf782c3773f77da", "config_sha256": "e3ca503938a39378fd50448c4273cee32a8923779ac081e8d6206b6e716abb7f", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "supertonic", "name": "Supertonic", "checkpoint": "Supertone/supertonic-3", "revision": "3cadd1ee6394adea1bd021217a0e650ede09a323", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.2797527089715004, "latency_p95_s": 0.3004460956901312, "rtf": 0.06423751407986668, "peak_vram_mib": 419.396484375, "audio_seconds": 4756.657505668934, "clipping_ratio": 0.0, "silence_ratio": 0.43568262751000425, "rms_dbfs": -26.68671776510351, "normalization_id": "whisper_english", "wer": 0.009796533534287867, "cer": 0.002663214902100815, "mer": 0.009789156626506024, "wil": 0.017839658400852665, "wip": 0.9821603415991473, "word_hits": 11835, "word_substitutions": 97, "word_deletions": 11, "word_insertions": 9, "reference_words": 11943, "char_hits": 67093, "char_substitutions": 63, "char_deletions": 56, "char_insertions": 60, "reference_chars": 67212, "exact_match_rate": 0.9099264705882353, "raw": { "wer": 0.04725609756097561, "cer": 0.011503733287028998, "mer": 0.047232097511427124, "wil": 0.08938259542996008, "wip": 0.9106174045700399, "word_hits": 11256, "word_substitutions": 521, "word_deletions": 31, "word_insertions": 6, "reference_words": 11808, "char_hits": 68422, "char_substitutions": 330, "char_deletions": 356, "char_insertions": 109, "reference_chars": 69108, "exact_match_rate": 0.6783088235294118 }, "orthographic": { "wer": 0.012187896741430384, "cer": 0.004784049207363276, "mer": 0.012184802843120663, "wil": 0.022815766562702122, "wip": 0.9771842334372979, "word_hits": 11674, "word_substitutions": 127, "word_deletions": 14, "word_insertions": 3, "reference_words": 11815, "char_hits": 67029, "char_substitutions": 100, "char_deletions": 178, "char_insertions": 44, "reference_chars": 67307, "exact_match_rate": 0.8878676470588235 }, "wer_ci95": [ 0.00785054517897158, 0.011805873826184896 ], "cer_ci95": [ 0.002118013958236292, 0.003225100490647234 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.009796533534287867, "cer": 0.002663214902100815, "mer": 0.009789156626506024, "wil": 0.017839658400852665, "wip": 0.9821603415991473, "word_hits": 11835, "word_substitutions": 97, "word_deletions": 11, "word_insertions": 9, "reference_words": 11943, "char_hits": 67093, "char_substitutions": 63, "char_deletions": 56, "char_insertions": 60, "reference_chars": 67212, "exact_match_rate": 0.9099264705882353 } }, "utterance_mean_wer": 0.009449587931955387, "utterance_mean_cer": 0.002529207763588537 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-supertonic-seedtts_en-000", "result_sha256": "61f1e7484a814f22b5fce12ad614a2ca4d9a5e2fefb25c3a112e8dda25e2d2a8", "config_sha256": "b0a62fb4dedb3fc17c6628a9b48dcb724dbbb4f87b00e5d71b3df8b660444677", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-supertonic-seedtts_en-001", "result_sha256": "937cc664440315417333e0acca9a4b7caa936426978ef862a7fafa733d541f08", "config_sha256": "84913533e59ff84279dbbe1a42f45b7580ac9fb3c5e0a06226ce1e483d5c3330", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-supertonic-seedtts_en-002", "result_sha256": "54e614676663b347309933eea6544fe51d709aa66d785e34cd97feed72727b0d", "config_sha256": "7e4d9fc06fe9ac79c3a175c62bcc09b547c9fbdfc99dd87d7cbc8c33ecf3721a", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-supertonic-seedtts_en-003", "result_sha256": "48a64d5856628a6fe8500438fa23a8250527d6c826d993781a62b18913befbf0", "config_sha256": "38291d0a927b167d67ec95449d7eb293e85c701df7fc36acecdb65b9d9a00123", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-supertonic-seedtts_en-004", "result_sha256": "05316f4324b2333d9e7798944e62fd450729e6ce01629b093d881fb40885fbb1", "config_sha256": "e1518dc7526044b48ccbafe7fc46d8badf2cd8bb005da59e7c776743e78b7528", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-supertonic-seedtts_en-005", "result_sha256": "2037ef5eee50edb5542dfe54eb8a403e88abae4846d913e9df5bee4fe8c0c5e3", "config_sha256": "10486e227846274ff0709a53f48c12a7829db857f802b42e5983bbaa6f3936c0", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "omnivoice", "name": "OmniVoice", "checkpoint": "k2-fsa/OmniVoice", "revision": "c5fdb5ccb189668d56333f77ba2629f4cd7535f4", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 1.332394178956747, "latency_p95_s": 1.5358351096510887, "rtf": 0.328981732833577, "peak_vram_mib": 3228.8759765625, "audio_seconds": 4436.8, "clipping_ratio": 0.0, "silence_ratio": 0.3348716952743415, "rms_dbfs": -23.852963743668997, "normalization_id": "whisper_english", "wer": 0.009880264590136481, "cer": 0.002648336606558353, "mer": 0.009874476987447698, "wil": 0.0173500167374373, "wip": 0.9826499832625627, "word_hits": 11832, "word_substitutions": 90, "word_deletions": 21, "word_insertions": 7, "reference_words": 11943, "char_hits": 67081, "char_substitutions": 46, "char_deletions": 85, "char_insertions": 47, "reference_chars": 67212, "exact_match_rate": 0.9154411764705882, "raw": { "wer": 0.05047425474254742, "cer": 0.011822075591827285, "mer": 0.05046998052332966, "wil": 0.09555917845872597, "wip": 0.904440821541274, "word_hits": 11213, "word_substitutions": 559, "word_deletions": 36, "word_insertions": 1, "reference_words": 11808, "char_hits": 68404, "char_substitutions": 329, "char_deletions": 375, "char_insertions": 113, "reference_chars": 69108, "exact_match_rate": 0.6617647058823529 }, "orthographic": { "wer": 0.011595429538721964, "cer": 0.00447204599818741, "mer": 0.011594448205822613, "wil": 0.021232262176693495, "wip": 0.9787677378233065, "word_hits": 11679, "word_substitutions": 115, "word_deletions": 21, "word_insertions": 1, "reference_words": 11815, "char_hits": 67037, "char_substitutions": 79, "char_deletions": 191, "char_insertions": 31, "reference_chars": 67307, "exact_match_rate": 0.8952205882352942 }, "wer_ci95": [ 0.007861317788115801, 0.012080484304594895 ], "cer_ci95": [ 0.0018904921536443545, 0.003657155632574282 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.009880264590136481, "cer": 0.002648336606558353, "mer": 0.009874476987447698, "wil": 0.0173500167374373, "wip": 0.9826499832625627, "word_hits": 11832, "word_substitutions": 90, "word_deletions": 21, "word_insertions": 7, "reference_words": 11943, "char_hits": 67081, "char_substitutions": 46, "char_deletions": 85, "char_insertions": 47, "reference_chars": 67212, "exact_match_rate": 0.9154411764705882 } }, "utterance_mean_wer": 0.009585752278766985, "utterance_mean_cer": 0.0024681703906616025 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-omnivoice-seedtts_en-000", "result_sha256": "07a9937d9053570193875ae2ff53decfefa8bf41d29fd83a9cbf99ebd6157ea8", "config_sha256": "d9ff68bd7a0db1c4a5cabcb815dea7578df75655f8bdfda8906916f671f19e90", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-omnivoice-seedtts_en-001", "result_sha256": "acef14cdfc3a50e411cf3cedbef2f8c24c5a26183ff46158e4232cbba66166f7", "config_sha256": "1b13a3a6fd88bce203061ad680b5b1cfa4a12b2d7e891cb5a9a095e7d28412be", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-omnivoice-seedtts_en-002", "result_sha256": "8b3ac8e98d90af2988f9c566e7ba880e5cd0a882d6487aa94beba7612a41889e", "config_sha256": "21a04b38e22bf97cb42eff0e227e1beea45e028d18d3bfaec93f0a00f28bf028", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-omnivoice-seedtts_en-003", "result_sha256": "40562f5b7cb6a1a4ac455d4872e3961c298c143ac32787bb1b0ab1e3e9c8bd56", "config_sha256": "e70328f2d96af5b5b9ed96144f11f7db77be9c6941813c2c19b779f561a07aac", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-omnivoice-seedtts_en-004", "result_sha256": "a25cd3aad81cf8226dc38fe29feab4b6d17c41f28a5eb7b50a599c014de5c054", "config_sha256": "446c2d8cf95be653ee1d7f2ba237e619544a4bae3ed4e3f17e48e16c636d31e0", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-omnivoice-seedtts_en-005", "result_sha256": "eed7b59b626ab76d36c1b3edcc119b7ed5632aa10b61baa708974956fee8700d", "config_sha256": "7cbce8b15e013341ab8e1ffba15225a3c196d5c8948a560c729edcd563b762f5", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "speecht5", "name": "SpeechT5", "checkpoint": "microsoft/speecht5_tts", "revision": "30fcde30f19b87502b8435427b5f5068e401d5f6", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.6036052946001291, "latency_p95_s": 0.9177474867552518, "rtf": 0.1622327560700419, "peak_vram_mib": 726.37158203125, "audio_seconds": 4101.024, "clipping_ratio": 0.0, "silence_ratio": 0.27561073823840104, "rms_dbfs": -25.413263645785655, "normalization_id": "whisper_english", "wer": 0.010131457757682325, "cer": 0.0029459025174076057, "mer": 0.010123828647925033, "wil": 0.01858563704868821, "wip": 0.9814143629513118, "word_hits": 11831, "word_substitutions": 102, "word_deletions": 10, "word_insertions": 9, "reference_words": 11943, "char_hits": 67066, "char_substitutions": 77, "char_deletions": 69, "char_insertions": 52, "reference_chars": 67212, "exact_match_rate": 0.90625, "raw": { "wer": 0.05377710027100271, "cer": 0.012661341668113677, "mer": 0.05372704966579237, "wil": 0.10168117284972034, "wip": 0.8983188271502797, "word_hits": 11184, "word_substitutions": 597, "word_deletions": 27, "word_insertions": 11, "reference_words": 11808, "char_hits": 68401, "char_substitutions": 383, "char_deletions": 324, "char_insertions": 168, "reference_chars": 69108, "exact_match_rate": 0.6433823529411765 }, "orthographic": { "wer": 0.012357173085061363, "cer": 0.004754334616013193, "mer": 0.012348811638332064, "wil": 0.02305833832692339, "wip": 0.9769416616730766, "word_hits": 11677, "word_substitutions": 128, "word_deletions": 10, "word_insertions": 8, "reference_words": 11815, "char_hits": 67034, "char_substitutions": 107, "char_deletions": 166, "char_insertions": 47, "reference_chars": 67307, "exact_match_rate": 0.8832720588235294 }, "wer_ci95": [ 0.008283238600798748, 0.012222576854350246 ], "cer_ci95": [ 0.00235856560816167, 0.003572732489586244 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.010131457757682325, "cer": 0.0029459025174076057, "mer": 0.010123828647925033, "wil": 0.01858563704868821, "wip": 0.9814143629513118, "word_hits": 11831, "word_substitutions": 102, "word_deletions": 10, "word_insertions": 9, "reference_words": 11943, "char_hits": 67066, "char_substitutions": 77, "char_deletions": 69, "char_insertions": 52, "reference_chars": 67212, "exact_match_rate": 0.90625 } }, "utterance_mean_wer": 0.009766929608381814, "utterance_mean_cer": 0.002814133144678633 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-speecht5-seedtts_en-000", "result_sha256": "af41e3808efa0187481db065267115f69e62bd494eb01871e277bb25137a084c", "config_sha256": "ec0b03378772b5af15d8a50cdedb5f5786874325614058ab5f95e5ecb3a21b02", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-speecht5-seedtts_en-001", "result_sha256": "6838a88ab1a9ceee4fd302eabf6ebf017bd0f369947dd3c15649ae8c353e2f28", "config_sha256": "3697a8ab63373c24d0a8a383b3d4be9bd656d1b0d73ab0c69ce32564a6580348", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-speecht5-seedtts_en-002", "result_sha256": "0ad8491f7e862bce410b06eb1c2b4e2515331f8d744995d45691d1e6277a8836", "config_sha256": "5cafe6811047095546af2512aecb95bac7c20e594ba21b91a06854719409261d", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-speecht5-seedtts_en-003", "result_sha256": "abfff491e6fe1aabedeedd4186ace18cced15e0767e240f67bff4b26d85abeb1", "config_sha256": "d14dfbf22a8b59720cb85cf000a4898b79b08137b13f9b7e9262d89786468cc0", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-speecht5-seedtts_en-004", "result_sha256": "e7079c5f3d9954b2999ed3936768e7409383fcd88dbf5956adda5ec4bb012452", "config_sha256": "d1ea9a80efcf6ab8ba8a2a95e3a7b28f2aa16308fedc2e8c09d4a4d6211c7c2e", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-speecht5-seedtts_en-005", "result_sha256": "35a1875bbbd8a621c242de92f9bd14fb47e1748af05b6b21765d803fbf2d94ae", "config_sha256": "77615ed6d414d47f9e353d6fe728be871ce3b2540f996213cf1f93c6c7c85d4a", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "f5tts", "name": "F5TTS", "checkpoint": "F5TTS_v1_Base", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 2.7469177208840847, "latency_p95_s": 2.9705387711524964, "rtf": 0.7815442867831554, "peak_vram_mib": 1516.4052734375, "audio_seconds": 3739.3813333333333, "clipping_ratio": 3.4988988015009135e-06, "silence_ratio": 0.21193145480339617, "rms_dbfs": -19.899939920591734, "normalization_id": "whisper_english", "wer": 0.010550113036925395, "cer": 0.0031988335416294708, "mer": 0.010543933054393306, "wil": 0.018842870213572005, "wip": 0.981157129786428, "word_hits": 11824, "word_substitutions": 100, "word_deletions": 19, "word_insertions": 7, "reference_words": 11943, "char_hits": 67046, "char_substitutions": 73, "char_deletions": 93, "char_insertions": 49, "reference_chars": 67212, "exact_match_rate": 0.9090073529411765, "raw": { "wer": 0.04361449864498645, "cer": 0.011330092029866297, "mer": 0.04359972908906197, "wil": 0.08187955268207969, "wip": 0.9181204473179203, "word_hits": 11297, "word_substitutions": 471, "word_deletions": 40, "word_insertions": 4, "reference_words": 11808, "char_hits": 68387, "char_substitutions": 327, "char_deletions": 394, "char_insertions": 62, "reference_chars": 69108, "exact_match_rate": 0.7159926470588235 }, "orthographic": { "wer": 0.013034278459585272, "cer": 0.005363483738689884, "mer": 0.013032072438013033, "wil": 0.023829448845037793, "wip": 0.9761705511549622, "word_hits": 11663, "word_substitutions": 129, "word_deletions": 23, "word_insertions": 2, "reference_words": 11815, "char_hits": 66981, "char_substitutions": 109, "char_deletions": 217, "char_insertions": 35, "reference_chars": 67307, "exact_match_rate": 0.8851102941176471 }, "wer_ci95": [ 0.008544055321581331, 0.012617792351167754 ], "cer_ci95": [ 0.002511205039574283, 0.0039833394587379875 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.010550113036925395, "cer": 0.0031988335416294708, "mer": 0.010543933054393306, "wil": 0.018842870213572005, "wip": 0.981157129786428, "word_hits": 11824, "word_substitutions": 100, "word_deletions": 19, "word_insertions": 7, "reference_words": 11943, "char_hits": 67046, "char_substitutions": 73, "char_deletions": 93, "char_insertions": 49, "reference_chars": 67212, "exact_match_rate": 0.9090073529411765 } }, "utterance_mean_wer": 0.011274173130790778, "utterance_mean_cer": 0.004422374102850214 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-f5tts-seedtts_en-000", "result_sha256": "27a883187f95316646ef814ee3e8fe3354de2919b520a5472cfcd93a1fd65d79", "config_sha256": "f10f1d92de9c5a16457d43e0785b999b714d7687f8aecb93b40d2aba259e051e", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-f5tts-seedtts_en-001", "result_sha256": "6eb1bbe6d966c2001110b4b10586acc23f16ec0fc544305573966b5350d030a5", "config_sha256": "d51a4e4cb12b6d4cfc6d1bfe17ae0d5bfaf15d13779872d035f992914f2e0bea", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-f5tts-seedtts_en-002", "result_sha256": "5ae930a87986c75d403f4993123a37c6402a737697557131d8e759141f2aa796", "config_sha256": "d10a2155d9381a498327e21b3b713fbfc1b94b4a0562db30da412b2a7318e4cb", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-f5tts-seedtts_en-003", "result_sha256": "e6139058608689ba6ce337458d19b1979a348f0d6397bea728f10a2d9ef5eedf", "config_sha256": "9ab101dad1a62d013159d9fe550a70de56eace44fdf06c19c0f6990db272461a", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-f5tts-seedtts_en-004", "result_sha256": "5e942f992265e139167631ff687e8ef5545c03cedba7bd24a2bd32a345ecc382", "config_sha256": "6df38f583c53050fb84b9ade163aecf5b78facabfa4d1b102f260a0d339c5580", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-f5tts-seedtts_en-005", "result_sha256": "49b7504dbf6ff85e6ffb7e5651410c6c679600310dcfcc866efc2e380eac7905", "config_sha256": "2caf03f93347de9941029cc77a46cf31f1fc813adb01fe427c1da954a7f7ba59", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "styletts2", "name": "StyleTTS2", "checkpoint": "artifacts/styletts2/epochs_2nd_00020.pth", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.19795850105583668, "latency_p95_s": 0.2473351741209626, "rtf": 0.04208604152148397, "peak_vram_mib": 1068.0185546875, "audio_seconds": 5058.533333333333, "clipping_ratio": 0.0, "silence_ratio": 0.29950891529922624, "rms_dbfs": -22.315291148181117, "normalization_id": "whisper_english", "wer": 0.010885037260319853, "cer": 0.0029905374040349935, "mer": 0.010876840696117804, "wil": 0.019831987068541723, "wip": 0.9801680129314583, "word_hits": 11822, "word_substitutions": 108, "word_deletions": 13, "word_insertions": 9, "reference_words": 11943, "char_hits": 67072, "char_substitutions": 78, "char_deletions": 62, "char_insertions": 61, "reference_chars": 67212, "exact_match_rate": 0.9044117647058824, "raw": { "wer": 0.05123644986449864, "cer": 0.012502170515714534, "mer": 0.051193095278388896, "wil": 0.09678668317877503, "wip": 0.903213316821225, "word_hits": 11213, "word_substitutions": 566, "word_deletions": 29, "word_insertions": 10, "reference_words": 11808, "char_hits": 68372, "char_substitutions": 386, "char_deletions": 350, "char_insertions": 128, "reference_chars": 69108, "exact_match_rate": 0.6516544117647058 }, "orthographic": { "wer": 0.013542107490478206, "cer": 0.0051703388949143475, "mer": 0.013534088986635088, "wil": 0.02507145803641664, "wip": 0.9749285419635834, "word_hits": 11662, "word_substitutions": 138, "word_deletions": 15, "word_insertions": 7, "reference_words": 11815, "char_hits": 67013, "char_substitutions": 111, "char_deletions": 183, "char_insertions": 54, "reference_chars": 67307, "exact_match_rate": 0.8795955882352942 }, "wer_ci95": [ 0.008889246341617306, 0.01317792950459316 ], "cer_ci95": [ 0.0023622418836487065, 0.003664567204361421 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.010885037260319853, "cer": 0.0029905374040349935, "mer": 0.010876840696117804, "wil": 0.019831987068541723, "wip": 0.9801680129314583, "word_hits": 11822, "word_substitutions": 108, "word_deletions": 13, "word_insertions": 9, "reference_words": 11943, "char_hits": 67072, "char_substitutions": 78, "char_deletions": 62, "char_insertions": 61, "reference_chars": 67212, "exact_match_rate": 0.9044117647058824 } }, "utterance_mean_wer": 0.010743798174864353, "utterance_mean_cer": 0.0029116890397277357 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-styletts2-seedtts_en-000", "result_sha256": "316f9d7402090f646ff8fe0c26e2791ae1ff4974f83e82a1d760afbc1fee06e5", "config_sha256": "3060f43c87944f8cdf9926555c249ce3550a0e0d8550fc49bc0e5c9b4a6a09ae", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-styletts2-seedtts_en-001", "result_sha256": "e33b0b7aa0fe9641e309eeb9314fc33ec05f9e992cacdbeb52a677db598f7245", "config_sha256": "15cbade12c9c1c699b7c0413288385df3880eb5bbaaf31a4ee0df358d7a0353f", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-styletts2-seedtts_en-002", "result_sha256": "a8a599b800750e7bf88c14fa6f763d03d15ca290149029fd3b174a8859033875", "config_sha256": "d88e57c2e1fadde3461173611ae0a945fd42cc6dd4e347ed91ce553876e039f4", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-styletts2-seedtts_en-003", "result_sha256": "751f9cf5978b142f12e730d04811f92deae67afca36c2c74bd7e30a3b1bf7d5d", "config_sha256": "731b6ee04e29a1e0ffb90e8e4b019a490e8721ea9c3db5ccd121c08370213d50", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-styletts2-seedtts_en-004", "result_sha256": "11093f74b147055cc56420e8720568baa0ea707d7beedc914033dc304f4898e8", "config_sha256": "5887debf9ae2863e2bf999537eb5fc31b214ecea01a8f833fe4a8c1b580437a1", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-styletts2-seedtts_en-005", "result_sha256": "c5b2e9a58acda49c8df4c8ac9249b0f8101e779b2ccc18196392078a7d12f784", "config_sha256": "f798544a12eafe2528550bcb6f3aba33f10db3c0ef432d274472d21bf8b13d91", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "echo", "name": "EchoTTS", "checkpoint": "jordand/echo-tts-base", "revision": "06731f67000241d55cff6b0a961f22f5f151f24f", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 2.456841016188264, "latency_p95_s": 2.5182850835844874, "rtf": 0.5723286716880129, "peak_vram_mib": 9363.14453125, "audio_seconds": 4676.359546485261, "clipping_ratio": 0.0, "silence_ratio": 0.12887222618488867, "rms_dbfs": -13.952829189004829, "normalization_id": "whisper_english", "wer": 0.01121996148371431, "cer": 0.0034815211569362613, "mer": 0.011207761793241887, "wil": 0.020324327635941386, "wip": 0.9796756723640586, "word_hits": 11822, "word_substitutions": 110, "word_deletions": 11, "word_insertions": 13, "reference_words": 11943, "char_hits": 67046, "char_substitutions": 92, "char_deletions": 74, "char_insertions": 68, "reference_chars": 67212, "exact_match_rate": 0.9034926470588235, "raw": { "wer": 0.07647357723577236, "cer": 0.017725878335359147, "mer": 0.0764218009478673, "wil": 0.1442527165227956, "wip": 0.8557472834772044, "word_hits": 10913, "word_substitutions": 865, "word_deletions": 30, "word_insertions": 8, "reference_words": 11808, "char_hits": 68015, "char_substitutions": 609, "char_deletions": 484, "char_insertions": 132, "reference_chars": 69108, "exact_match_rate": 0.5 }, "orthographic": { "wer": 0.013711383834109183, "cer": 0.005601200469490543, "mer": 0.013703265098968026, "wil": 0.025405824334897242, "wip": 0.9745941756651028, "word_hits": 11660, "word_substitutions": 140, "word_deletions": 15, "word_insertions": 7, "reference_words": 11815, "char_hits": 66980, "char_substitutions": 129, "char_deletions": 198, "char_insertions": 50, "reference_chars": 67307, "exact_match_rate": 0.8805147058823529 }, "wer_ci95": [ 0.008904209796796562, 0.013934323157998304 ], "cer_ci95": [ 0.0025651236034547214, 0.0047400288829906 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.01121996148371431, "cer": 0.0034815211569362613, "mer": 0.011207761793241887, "wil": 0.020324327635941386, "wip": 0.9796756723640586, "word_hits": 11822, "word_substitutions": 110, "word_deletions": 11, "word_insertions": 13, "reference_words": 11943, "char_hits": 67046, "char_substitutions": 92, "char_deletions": 74, "char_insertions": 68, "reference_chars": 67212, "exact_match_rate": 0.9034926470588235 } }, "utterance_mean_wer": 0.011593386444029826, "utterance_mean_cer": 0.003852356493516786 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-echo-seedtts_en-000", "result_sha256": "9edf6308e5f41f589b38784fe76036b4053e0806f9687686d5b8e1fd6a6dea32", "config_sha256": "73c3791000cceb12c51906033bd08a1787bf1553f8c387253570a75bddde8a5f", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-echo-seedtts_en-001", "result_sha256": "0328d2058b8206f3be8ccbaf273849f17aba8eb8b19d4fa894fceb212776a0bc", "config_sha256": "7fc481f3d3756dcab3fd2a381cea80d603ab77e25c84ad652afd7c375aeea165", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-echo-seedtts_en-002", "result_sha256": "5f823434734212f3442b1af2c16d8ed74dbef23fb9d43126e3b4fd4cb64a2365", "config_sha256": "63a47b008d6d8646fd2c12c8cb293c3b3bbe6b6aa11c47f257b4b0ecffb58733", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-echo-seedtts_en-003", "result_sha256": "e2ff5a6c5ed0179869103ec5dbebaf95dd3448b1046e0593063b7386c807f804", "config_sha256": "ce17af283cdc7a4b6e1f6c8b60095e95b4acc58885e31d8974398c87905fcdab", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-echo-seedtts_en-004", "result_sha256": "f2323011620e2bb3664e806b3aae1835b12c9b85acd8ae558b005d503b4994a9", "config_sha256": "1cc0c1738c5f2d14eda62e8c8bddc2e8e05cc0a270b95feaf38c5dbbb9c74679", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-echo-seedtts_en-005", "result_sha256": "78bb955606e9a5eb3f2189fc68c501449a22e4ce17fe8ac86e57d99925fd9c4f", "config_sha256": "c66248faa466eb76ae93dcbe8a39b7a137fa14fcd5aca9f7bfcfb85abca471d7", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "fishtts", "name": "FishTTS", "checkpoint": "fishaudio/s2-pro", "revision": "1de9996b6be38b745688de084d87a5633f714e4e", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 14.975895503535867, "latency_p95_s": 21.895659835077815, "rtf": 3.7434938590228506, "peak_vram_mib": 14652.67431640625, "audio_seconds": 4357.735328798186, "clipping_ratio": 0.0, "silence_ratio": 0.13489419262981148, "rms_dbfs": -16.634614222894925, "normalization_id": "whisper_english", "wer": 0.011471154651260152, "cer": 0.0031690769505445457, "mer": 0.011463475859760689, "wil": 0.020912083738239273, "wip": 0.9790879162617607, "word_hits": 11814, "word_substitutions": 114, "word_deletions": 15, "word_insertions": 8, "reference_words": 11943, "char_hits": 67050, "char_substitutions": 95, "char_deletions": 67, "char_insertions": 51, "reference_chars": 67212, "exact_match_rate": 0.8970588235294118, "raw": { "wer": 0.05013550135501355, "cer": 0.012183828210916247, "mer": 0.05011852353538774, "wil": 0.0951981254515083, "wip": 0.9048018745484917, "word_hits": 11220, "word_substitutions": 559, "word_deletions": 29, "word_insertions": 4, "reference_words": 11808, "char_hits": 68349, "char_substitutions": 382, "char_deletions": 377, "char_insertions": 83, "reference_chars": 69108, "exact_match_rate": 0.65625 }, "orthographic": { "wer": 0.013118916631400761, "cer": 0.004977194051138812, "mer": 0.013116696285013116, "wil": 0.024658422728009777, "wip": 0.9753415772719902, "word_hits": 11662, "word_substitutions": 138, "word_deletions": 15, "word_insertions": 2, "reference_words": 11815, "char_hits": 67009, "char_substitutions": 125, "char_deletions": 173, "char_insertions": 37, "reference_chars": 67307, "exact_match_rate": 0.8805147058823529 }, "wer_ci95": [ 0.009372852661418718, 0.013923650739157823 ], "cer_ci95": [ 0.0025164327337067866, 0.003856638680410998 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.011471154651260152, "cer": 0.0031690769505445457, "mer": 0.011463475859760689, "wil": 0.020912083738239273, "wip": 0.9790879162617607, "word_hits": 11814, "word_substitutions": 114, "word_deletions": 15, "word_insertions": 8, "reference_words": 11943, "char_hits": 67050, "char_substitutions": 95, "char_deletions": 67, "char_insertions": 51, "reference_chars": 67212, "exact_match_rate": 0.8970588235294118 } }, "utterance_mean_wer": 0.010823033686085157, "utterance_mean_cer": 0.002976193604265695 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-fishtts-seedtts_en-000", "result_sha256": "d252e80b4fc961551544f996295fb43612013185470710ceb15ef44678787686", "config_sha256": "863b2c507061479d3415793d85eb443d3ec7df553c88dff03604636544c3cd7f", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-fishtts-seedtts_en-001", "result_sha256": "ac5e72a9d027c204c179df805b62d2d76219c72089f532b4b2add392dd36c88d", "config_sha256": "7c06b46f52929108cec6f5bce873ef51377dedcc832cc63f07e5b5e632ae1411", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-fishtts-seedtts_en-002", "result_sha256": "03958e2fb8286619d3bdb78a8a9b31dd7e2ce8328795e1c778d0222cfe40943d", "config_sha256": "dd5a41a07e021dee1b9f5cc917bd642ab36d4fd8a662902279a11176e0afef61", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-fishtts-seedtts_en-003", "result_sha256": "dc5ca876e29b7e90d5a7b9bb4157c25aeda74c31e3fe604a5138f104983cfefa", "config_sha256": "79e9f2de82ce59fbc1cf15ef12875154644c7221ed4b7920f61e12658be67467", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-fishtts-seedtts_en-004", "result_sha256": "5d47ba1fb463a8d99859e22a5767580d19900a322c73ad905e0d689c588a44c3", "config_sha256": "88c16f6f8f349535d5c7ae3b0884774180942b089b262f5079c1287ce8338a52", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-fishtts-seedtts_en-005", "result_sha256": "ab4092314a63f4f3b4314d93da955f1de6dd9317335199b8376844e140e6383e", "config_sha256": "14f7c37de4241c134a1819b8b74d79beb4e4923cac9dd19deec8cfc419c926d1", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "xtts", "name": "XTTS", "checkpoint": "artifacts/xtts2", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 1.377348417416215, "latency_p95_s": 2.1737355709075925, "rtf": 0.37659089175029953, "peak_vram_mib": 2044.58837890625, "audio_seconds": 4109.9946666666665, "clipping_ratio": 0.0, "silence_ratio": 0.12863922070376485, "rms_dbfs": -17.494293341348765, "normalization_id": "whisper_english", "wer": 0.011722347818805995, "cer": 0.003927870023210141, "mer": 0.011700793982448809, "wil": 0.020155170204901096, "wip": 0.9798448297950989, "word_hits": 11825, "word_substitutions": 102, "word_deletions": 16, "word_insertions": 22, "reference_words": 11943, "char_hits": 67063, "char_substitutions": 80, "char_deletions": 69, "char_insertions": 115, "reference_chars": 67212, "exact_match_rate": 0.8979779411764706, "raw": { "wer": 0.05809620596205962, "cer": 0.014195172773050877, "mer": 0.05803722504230118, "wil": 0.10939329118859553, "wip": 0.8906067088114045, "word_hits": 11134, "word_substitutions": 642, "word_deletions": 32, "word_insertions": 12, "reference_words": 11808, "char_hits": 68345, "char_substitutions": 427, "char_deletions": 336, "char_insertions": 218, "reference_chars": 69108, "exact_match_rate": 0.6121323529411765 }, "orthographic": { "wer": 0.014049936521371138, "cer": 0.005838917200291203, "mer": 0.014032121724429417, "wil": 0.024984772654058962, "wip": 0.975015227345941, "word_hits": 11664, "word_substitutions": 131, "word_deletions": 20, "word_insertions": 15, "reference_words": 11815, "char_hits": 67012, "char_substitutions": 112, "char_deletions": 183, "char_insertions": 98, "reference_chars": 67307, "exact_match_rate": 0.875 }, "wer_ci95": [ 0.009479942028329125, 0.013929717071918904 ], "cer_ci95": [ 0.003047702271545646, 0.004894855067600172 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.011722347818805995, "cer": 0.003927870023210141, "mer": 0.011700793982448809, "wil": 0.020155170204901096, "wip": 0.9798448297950989, "word_hits": 11825, "word_substitutions": 102, "word_deletions": 16, "word_insertions": 22, "reference_words": 11943, "char_hits": 67063, "char_substitutions": 80, "char_deletions": 69, "char_insertions": 115, "reference_chars": 67212, "exact_match_rate": 0.8979779411764706 } }, "utterance_mean_wer": 0.012030761823960354, "utterance_mean_cer": 0.003932957956043187 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-xtts-seedtts_en-000", "result_sha256": "f907823ffddf051bd15d488c04cd1baf4ae71e9ebdb6088bc8bb3c3e5c5bf674", "config_sha256": "59354a13046e0ffe3bbbc67dd3bdae714249b9630dcc5f43b1d8592d4e09df55", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-xtts-seedtts_en-001", "result_sha256": "572b02b0030cbc0f3d845a58986474ac47624a58a16d28c71778b33451398980", "config_sha256": "e2aa5bdb9871647fb54c7df3e155fceb973d054f4d4e20d365df81fa12a43f4a", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-xtts-seedtts_en-002", "result_sha256": "cc202239c3d0fb3f1aabc8c9c995e3e9e94ef474d01171435c9054ce7e52860b", "config_sha256": "053336f43ad0e2161056d99de5adf5a1a5efb9cf1ccdb65965e79c5facf6cea3", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-xtts-seedtts_en-003", "result_sha256": "2a5e5588ffd2a6f673f0c3a665ffd47036a5e4f3d705973dbe94871df3c5c57b", "config_sha256": "f53a888f3a7be62165016c9dfb9a16e968a315603de67807cc486b21eb44f24a", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-xtts-seedtts_en-004", "result_sha256": "8d9df39feddef00fee250808a810e2886ddecf1345c382554de8c7af43eac25a", "config_sha256": "a924116ab55a218b9c60e90cd59e8fb73affacb456fa491b7e0cbe7d8613a856", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-xtts-seedtts_en-005", "result_sha256": "c0f03fd8a4d3440f3b0c42374763c82f9c0208c3b6232f3a683207ca19f567f3", "config_sha256": "78d8c393cc0c93c6fc4d8ae0c229a0091717ad503553eea1f2e6c24e3af84627", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "zonos2", "name": "Zonos2", "checkpoint": "Zyphra/ZONOS2", "revision": "65f1e80f94b599d474bb6af9094a803dc52f60bd", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "generation_limit_rate": 0.0, "generation_limit_samples": 0, "generation_limit_checks": 1088, "latency_p50_s": 21.817871015518904, "latency_p95_s": 32.1434196209535, "rtf": 6.227715330972293, "peak_vram_mib": 15765.91650390625, "audio_seconds": 3808.4556916099773, "clipping_ratio": 0.0, "silence_ratio": 0.1599482895773222, "rms_dbfs": -21.204251726272272, "normalization_id": "whisper_english", "wer": 0.01180607887465461, "cer": 0.004210557638516931, "mer": 0.01179817588486319, "wil": 0.020508167521017695, "wip": 0.9794918324789823, "word_hits": 11810, "word_substitutions": 105, "word_deletions": 28, "word_insertions": 8, "reference_words": 11943, "char_hits": 66986, "char_substitutions": 78, "char_deletions": 148, "char_insertions": 57, "reference_chars": 67212, "exact_match_rate": 0.9034926470588235, "raw": { "wer": 0.05013550135501355, "cer": 0.01292180355385773, "mer": 0.05011852353538774, "wil": 0.09373678274355002, "wip": 0.90626321725645, "word_hits": 11220, "word_substitutions": 540, "word_deletions": 48, "word_insertions": 4, "reference_words": 11808, "char_hits": 68338, "char_substitutions": 355, "char_deletions": 415, "char_insertions": 123, "reference_chars": 69108, "exact_match_rate": 0.6599264705882353 }, "orthographic": { "wer": 0.014049936521371138, "cer": 0.006121205818116987, "mer": 0.014046369944152986, "wil": 0.025256701027486117, "wip": 0.9747432989725139, "word_hits": 11652, "word_substitutions": 134, "word_deletions": 29, "word_insertions": 3, "reference_words": 11815, "char_hits": 66941, "char_substitutions": 108, "char_deletions": 258, "char_insertions": 46, "reference_chars": 67307, "exact_match_rate": 0.8795955882352942 }, "wer_ci95": [ 0.009429594420391598, 0.01437212173948811 ], "cer_ci95": [ 0.0030648629407874664, 0.0057465328607648365 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.01180607887465461, "cer": 0.004210557638516931, "mer": 0.01179817588486319, "wil": 0.020508167521017695, "wip": 0.9794918324789823, "word_hits": 11810, "word_substitutions": 105, "word_deletions": 28, "word_insertions": 8, "reference_words": 11943, "char_hits": 66986, "char_substitutions": 78, "char_deletions": 148, "char_insertions": 57, "reference_chars": 67212, "exact_match_rate": 0.9034926470588235 } }, "utterance_mean_wer": 0.011642725636291814, "utterance_mean_cer": 0.004352088341262807 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-zonos2-seedtts_en-000", "result_sha256": "2b2b25a6d39fddd1b5ad315a7b99e8b22b4f9f47b3188773c1ab6499b2cc61e2", "config_sha256": "a265ebb598ea66e2ed3f8f874b3e3b57dddc863a7292f46eaca6f49234dd8487", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-zonos2-seedtts_en-001", "result_sha256": "cb7f81b14479530040d6d1cc711211fd0a2b0edf76ab508db47e3edae08ef90d", "config_sha256": "9ca3f421cd1c6155d5fbdf8d6ab05bed4342b2797ff00e34534262d829425ade", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-zonos2-seedtts_en-002", "result_sha256": "fbad9c8a47d92a4651d178adeb6f068a715626550b96de79a564306678710c55", "config_sha256": "6cdcd111ed1c7303224e1efae8175f724882143ae0f5140e2fd3e759fefcffa6", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-zonos2-seedtts_en-003", "result_sha256": "09741a9b237d81fe9df1b8ec6c987af389c72038b8185f4ce90569fe14a41e2a", "config_sha256": "51122621b8f68cd8d88a2fe12374bbe84ce972d6c04510fca1da8e5826901089", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-zonos2-seedtts_en-004", "result_sha256": "c3fb4a85badee1978c1a9d137154e7416eb005db395acc2d34eebc3c66020879", "config_sha256": "972798e06746ff6750bc9dbaa151f329b3fd941925a4cc2fe1376204e4671e29", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-zonos2-seedtts_en-005", "result_sha256": "1212a42060f96e8a0dfd065fb766883df5696c6760bf0c8a762d9dc97abe71bc", "config_sha256": "b220206296f1662022a6a51703b26c13fa12d9316fb8a73fb538d46383b1dbbf", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "chatterbox", "name": "Chatterbox", "checkpoint": "ResembleAI/chatterbox", "revision": "5bb1f6ee58e50c3b8d408bc82a6d3740c2db6e18", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 2.598566422238946, "latency_p95_s": 3.5963106857612717, "rtf": 0.8215815223732541, "peak_vram_mib": 3243.5419921875, "audio_seconds": 3491.6, "clipping_ratio": 3.745316243777417e-06, "silence_ratio": 0.14410049492526528, "rms_dbfs": -17.46151259613592, "normalization_id": "whisper_english", "wer": 0.012308465209746294, "cer": 0.0035261560435636496, "mer": 0.012300225922516944, "wil": 0.022405080632642016, "wip": 0.977594919367358, "word_hits": 11804, "word_substitutions": 122, "word_deletions": 17, "word_insertions": 8, "reference_words": 11943, "char_hits": 67033, "char_substitutions": 91, "char_deletions": 88, "char_insertions": 58, "reference_chars": 67212, "exact_match_rate": 0.8851102941176471, "raw": { "wer": 0.05496273712737127, "cer": 0.01331249638247381, "mer": 0.054948776564219794, "wil": 0.10430035635245993, "wip": 0.8956996436475401, "word_hits": 11162, "word_substitutions": 615, "word_deletions": 31, "word_insertions": 3, "reference_words": 11808, "char_hits": 68318, "char_substitutions": 400, "char_deletions": 390, "char_insertions": 130, "reference_chars": 69108, "exact_match_rate": 0.6102941176470589 }, "orthographic": { "wer": 0.014980956411341515, "cer": 0.005809202608941121, "mer": 0.014978420919014978, "wil": 0.028252517243297137, "wip": 0.9717474827567029, "word_hits": 11640, "word_substitutions": 159, "word_deletions": 16, "word_insertions": 2, "reference_words": 11815, "char_hits": 66959, "char_substitutions": 132, "char_deletions": 216, "char_insertions": 43, "reference_chars": 67307, "exact_match_rate": 0.8584558823529411 }, "wer_ci95": [ 0.010239624689752567, 0.014502005846153599 ], "cer_ci95": [ 0.002878993025473877, 0.004195101111888829 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.012308465209746294, "cer": 0.0035261560435636496, "mer": 0.012300225922516944, "wil": 0.022405080632642016, "wip": 0.977594919367358, "word_hits": 11804, "word_substitutions": 122, "word_deletions": 17, "word_insertions": 8, "reference_words": 11943, "char_hits": 67033, "char_substitutions": 91, "char_deletions": 88, "char_insertions": 58, "reference_chars": 67212, "exact_match_rate": 0.8851102941176471 } }, "utterance_mean_wer": 0.011868301735029677, "utterance_mean_cer": 0.0034512612340441458 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-chatterbox-seedtts_en-000", "result_sha256": "7a3f83029980628b58f3d9cace44b59be6495050dd966ffb4f2b9065bf86f073", "config_sha256": "47f65fb9230e89e507e8a9bee36e06c1493d90ef5190766c902d89fbd995e30a", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-chatterbox-seedtts_en-001", "result_sha256": "ca8a90455a6c6e082d84264dae0e59cb21478d416df20f096190fb4f4d28b0b4", "config_sha256": "7616e53f69b116245f655805f352180ad366e411b821deb8a1283865ef77b4c3", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-chatterbox-seedtts_en-002", "result_sha256": "01a294994307b807495f0f84c0f94dbf759ee431db215778f260f4438995edf7", "config_sha256": "ce984dcc1a4e378bb1ae6c0abf0ee8d1a57f8794c39622c10597c930ecf555fa", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-chatterbox-seedtts_en-003", "result_sha256": "0910e2bc078efa4d7b39c2ceb67371f5e2cfbe1694d124ae0601d95b7f486746", "config_sha256": "881a7e4018f3511d422c7d09239bd7301c50da2042dca3ca8f1177797b6fbeee", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-chatterbox-seedtts_en-004", "result_sha256": "011526a95a1ec3d51f25b5ecb7cb7769fea048cbc6825115ec7ae18b91e728ec", "config_sha256": "fd03172df561742576c7afd7bcb9681117de95b6666e83ee0629b242f3b9885d", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-chatterbox-seedtts_en-005", "result_sha256": "94df7c218c2f61ca15012e60a8fed7d2680084ce732077c413e2231eca549fb0", "config_sha256": "b9d4032fb6e6afda80c7852e11d44090012bfc14ee26ca73f2f3ed56ad030cc3", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "mosstts", "name": "MossTTS", "checkpoint": "OpenMOSS-Team/MOSS-TTS-v1.5", "revision": "cdd3b911b1585e3f2dbc7775ef10f9926f58850a", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 7.407788587734103, "latency_p95_s": 10.18555185869335, "rtf": 1.389709319705265, "peak_vram_mib": 25009.28662109375, "audio_seconds": 5986.0, "clipping_ratio": 4.602443648000904e-06, "silence_ratio": 0.43571122588738487, "rms_dbfs": -26.128175142768608, "normalization_id": "whisper_english", "wer": 0.012308465209746294, "cer": 0.00431470570731417, "mer": 0.012298167823977245, "wil": 0.021827881301883956, "wip": 0.978172118698116, "word_hits": 11806, "word_substitutions": 115, "word_deletions": 22, "word_insertions": 10, "reference_words": 11943, "char_hits": 66989, "char_substitutions": 122, "char_deletions": 101, "char_insertions": 67, "reference_chars": 67212, "exact_match_rate": 0.9080882352941176, "raw": { "wer": 0.08536585365853659, "cer": 0.019925334259420037, "mer": 0.08532249873031995, "wil": 0.1605952432709965, "wip": 0.8394047567290035, "word_hits": 10806, "word_substitutions": 969, "word_deletions": 33, "word_insertions": 6, "reference_words": 11808, "char_hits": 67861, "char_substitutions": 678, "char_deletions": 569, "char_insertions": 130, "reference_chars": 69108, "exact_match_rate": 0.5625 }, "orthographic": { "wer": 0.01388066017774016, "cer": 0.005764630721915997, "mer": 0.013873614753404958, "wil": 0.025081554011935014, "wip": 0.974918445988065, "word_hits": 11657, "word_substitutions": 134, "word_deletions": 24, "word_insertions": 6, "reference_words": 11815, "char_hits": 66973, "char_substitutions": 146, "char_deletions": 188, "char_insertions": 54, "reference_chars": 67307, "exact_match_rate": 0.8943014705882353 }, "wer_ci95": [ 0.009509180623730396, 0.015755375124648537 ], "cer_ci95": [ 0.002815820019341391, 0.006384203524120753 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.012308465209746294, "cer": 0.00431470570731417, "mer": 0.012298167823977245, "wil": 0.021827881301883956, "wip": 0.978172118698116, "word_hits": 11806, "word_substitutions": 115, "word_deletions": 22, "word_insertions": 10, "reference_words": 11943, "char_hits": 66989, "char_substitutions": 122, "char_deletions": 101, "char_insertions": 67, "reference_chars": 67212, "exact_match_rate": 0.9080882352941176 } }, "utterance_mean_wer": 0.012728509235862176, "utterance_mean_cer": 0.004697708975017243 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-mosstts-seedtts_en-000", "result_sha256": "d72f64744263e85ec09b28901caf83574e1fe2d70f0a0986e5d9ebe126da338e", "config_sha256": "e7917094bfb572e6ef154cc886f3e9950d3e015580608026b36045353e826765", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-mosstts-seedtts_en-001", "result_sha256": "d5a9f758ed143d98f222ba59e8fc38f069729cd8c3fd61830cd8d4f23b33f8c9", "config_sha256": "39180be6478b53a751a90bb713cc91d3f91f493cca512813eb1c0cbdbea84987", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-mosstts-seedtts_en-002", "result_sha256": "2eb4ebf74f038534b06a67715cb922dc340df810834c15bb52efde990af9b7fa", "config_sha256": "1ecb8c3aeb84d960e0b3ccde39f1638cb02fd41960fc4e7e836aad71ccf98acf", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-mosstts-seedtts_en-003", "result_sha256": "5c61a47485a2225c78f7dd618a6cc6b1191a16c38a5b2ef4e7acc036ddc5f2bb", "config_sha256": "d0a3044411d96a6626d1e3e694cebc439c5450cb2e92db9eef60f938aa8527ef", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-mosstts-seedtts_en-004", "result_sha256": "5323703ffde5f5cf8c72554f6a88e7ef6af7e1eda67207404af499fd1fdd275a", "config_sha256": "bf03723297c6f9da155de726b403caad5811793567751b1a64cf020879cb4d88", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-mosstts-seedtts_en-005", "result_sha256": "621336c13e657d6536649cc45855b3a8169c3029745ffd69eaee648323b84372", "config_sha256": "33ad1d9d8366ce7914f6fecac315b8d77cce03f6a9ec114f5dbf3dc505c0fe6d", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "outetts", "name": "OuteTTS", "checkpoint": "OuteAI/Llama-OuteTTS-1.0-1B", "revision": "f445d0d301c7fc9e47fd545eb9f9d2912afe7a77", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 14.944048950448632, "latency_p95_s": 20.17052680440247, "rtf": 3.164612982009557, "peak_vram_mib": 4373.70263671875, "audio_seconds": 5142.874, "clipping_ratio": 0.0, "silence_ratio": 0.3346259142214407, "rms_dbfs": -19.94094323546973, "normalization_id": "whisper_english", "wer": 0.012392196265594908, "cer": 0.00437421888948402, "mer": 0.012376651613982272, "wil": 0.0210828903062108, "wip": 0.9789171096937892, "word_hits": 11810, "word_substitutions": 105, "word_deletions": 28, "word_insertions": 15, "reference_words": 11943, "char_hits": 66995, "char_substitutions": 81, "char_deletions": 136, "char_insertions": 77, "reference_chars": 67212, "exact_match_rate": 0.8933823529411765, "raw": { "wer": 0.05233739837398374, "cer": 0.013500607744400069, "mer": 0.05226657645466847, "wil": 0.09722483907776258, "wip": 0.9027751609222374, "word_hits": 11206, "word_substitutions": 558, "word_deletions": 44, "word_insertions": 16, "reference_words": 11808, "char_hits": 68320, "char_substitutions": 369, "char_deletions": 419, "char_insertions": 145, "reference_chars": 69108, "exact_match_rate": 0.6580882352941176 }, "orthographic": { "wer": 0.01608125264494287, "cer": 0.006418351731617811, "mer": 0.016060862214708368, "wil": 0.028252517243297137, "wip": 0.9717474827567029, "word_hits": 11640, "word_substitutions": 146, "word_deletions": 29, "word_insertions": 15, "reference_words": 11815, "char_hits": 66957, "char_substitutions": 116, "char_deletions": 234, "char_insertions": 82, "reference_chars": 67307, "exact_match_rate": 0.8621323529411765 }, "wer_ci95": [ 0.010140987840998449, 0.014841937026503233 ], "cer_ci95": [ 0.003199460828193918, 0.0057059813442127735 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.012392196265594908, "cer": 0.00437421888948402, "mer": 0.012376651613982272, "wil": 0.0210828903062108, "wip": 0.9789171096937892, "word_hits": 11810, "word_substitutions": 105, "word_deletions": 28, "word_insertions": 15, "reference_words": 11943, "char_hits": 66995, "char_substitutions": 81, "char_deletions": 136, "char_insertions": 77, "reference_chars": 67212, "exact_match_rate": 0.8933823529411765 } }, "utterance_mean_wer": 0.01187204084722467, "utterance_mean_cer": 0.004199895383034018 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-outetts-seedtts_en-000", "result_sha256": "afeff7ec619ea7b8ad79b8e08f88c006eebee81a85e37ec16dee288e8a9045b1", "config_sha256": "97f0c1f55945c79ff2fa2f8ec5c4a9b011e631e140c0c1bbee19c6038986899b", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-outetts-seedtts_en-001", "result_sha256": "817f744e6efb4ce40e0ee6510c3aaacf51e5e0b6551f81fd6929551391436e49", "config_sha256": "fe7a8fc412f2e270d119c4827caaa1dfd1bdecf9e70bbc24f1e2aa3eadb851b2", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-outetts-seedtts_en-002", "result_sha256": "ad2cf74b1ae52d20d196a36b0333fb2ed2ef6ef3c2eb4b4297d1d1a9cdd5d958", "config_sha256": "25c41f3b7dc4a95e15ce22e4926c282947ff008865f2c45b6703711bbf6246a6", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-outetts-seedtts_en-003", "result_sha256": "d0277a3d3b8a53bc8b0da6bfd83190cc4125a26fa270220d45724baac371b623", "config_sha256": "7c5cde33944aa739d400baaf134441672ad00a7d30e3a6f3fcc3eb29d5be89cc", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-outetts-seedtts_en-004", "result_sha256": "fdf465132f33d45693e900b230587e08469fef98b8e7cb422626dc21128295c7", "config_sha256": "79c8cf9e283134ce08bce6b36ec1ebba3ca04a0d1b46e223e040998f1d26bd65", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-outetts-seedtts_en-005", "result_sha256": "317b028c3b0f23d70c92b41fb126a490a6db24d84550ea3405d3e951f578efa1", "config_sha256": "9199b65843ec15ab16889144548be0dff35544717ae0af57d6b60730764748be", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "vibevoice", "name": "VibeVoice", "checkpoint": "microsoft/VibeVoice-Realtime-0.5B", "revision": "6bce5f06044837fe6d2c5d7a71a84f0416bd57e4", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 2.793820545077324, "latency_p95_s": 4.0911998309195035, "rtf": 0.6212332774264896, "peak_vram_mib": 2034.2626953125, "audio_seconds": 4941.2, "clipping_ratio": 7.978451797385622e-09, "silence_ratio": 0.31937791229579665, "rms_dbfs": -26.039530312116856, "ttfa_p50_s": 0.06309791281819344, "ttfa_p95_s": 0.07142821289598941, "ttfa_samples": 1088, "normalization_id": "whisper_english", "wer": 0.013145775768232438, "cer": 0.004151044456347081, "mer": 0.013129285833751463, "wil": 0.023229322079901915, "wip": 0.9767706779200981, "word_hits": 11801, "word_substitutions": 122, "word_deletions": 20, "word_insertions": 15, "reference_words": 11943, "char_hits": 67020, "char_substitutions": 93, "char_deletions": 99, "char_insertions": 87, "reference_chars": 67212, "exact_match_rate": 0.8823529411764706, "raw": { "wer": 0.059027777777777776, "cer": 0.013905770677779707, "mer": 0.058987813134732565, "wil": 0.11103724429267559, "wip": 0.8889627557073244, "word_hits": 11119, "word_substitutions": 651, "word_deletions": 38, "word_insertions": 8, "reference_words": 11808, "char_hits": 68341, "char_substitutions": 406, "char_deletions": 361, "char_insertions": 194, "reference_chars": 69108, "exact_match_rate": 0.6139705882352942 }, "orthographic": { "wer": 0.01388066017774016, "cer": 0.005096052416539142, "mer": 0.01387126786771547, "wil": 0.025490449385964564, "wip": 0.9745095506140354, "word_hits": 11659, "word_substitutions": 139, "word_deletions": 17, "word_insertions": 8, "reference_words": 11815, "char_hits": 67034, "char_substitutions": 110, "char_deletions": 163, "char_insertions": 70, "reference_chars": 67307, "exact_match_rate": 0.8722426470588235 }, "wer_ci95": [ 0.010848131126616388, 0.015379696839116497 ], "cer_ci95": [ 0.003391400828390384, 0.00499105574195605 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.013145775768232438, "cer": 0.004151044456347081, "mer": 0.013129285833751463, "wil": 0.023229322079901915, "wip": 0.9767706779200981, "word_hits": 11801, "word_substitutions": 122, "word_deletions": 20, "word_insertions": 15, "reference_words": 11943, "char_hits": 67020, "char_substitutions": 93, "char_deletions": 99, "char_insertions": 87, "reference_chars": 67212, "exact_match_rate": 0.8823529411764706 } }, "utterance_mean_wer": 0.012995374453257238, "utterance_mean_cer": 0.004069196706291303 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-vibevoice-seedtts_en-000", "result_sha256": "e5e85513dcc72927cc03579f2b701ba698a778d1985826a17a506c1648b0f9ee", "config_sha256": "75f9b1110c08c0f2e51fee3b922bd7289b01bd32f52ed2b8e9117f4b46ac4de6", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-vibevoice-seedtts_en-001", "result_sha256": "7a90af43080a43c5dd0701cf6e381bd6f6f181989b2d302e2b20234a55fee636", "config_sha256": "0a81c37638695b7eafb8b96945f182e1cf13e8bf3fe9e3502cf28fdd24fbc2a9", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-vibevoice-seedtts_en-002", "result_sha256": "3c18c5a7c9da1b639f343948f21adb2d8ab7dd7dc8cc2d23d8ea3178600ff048", "config_sha256": "3c6aee60bcae6697f33d492ad3a7acae756de6630552f6022f04009ce68e33ce", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-vibevoice-seedtts_en-003", "result_sha256": "7486c5369e38d713093a371d08c1de14e66f246cc2f87e7f3bb970dcedebccb3", "config_sha256": "1d436c39b93d58513169187f3a370d6d83a74d2e85c81b67f4eb026ced9c64bf", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-vibevoice-seedtts_en-004", "result_sha256": "41811523b279ab7e91e267a148c76c3389eb9c194f797c460e586deeef5c0b81", "config_sha256": "f74fcbd5f57cba59d5f42b4d689e85cccbb70915fae99b115c0318ff5accdce5", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-vibevoice-seedtts_en-005", "result_sha256": "b062797f8d468ecb9d013b11346180a32edbcb5cd6d2532403541a7bcde1e7c6", "config_sha256": "6ae5e9b754dcadaeaefe0a5f1ee5aba63829fb2233eb7dada1195a80383c4966", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "qwen3tts", "name": "Qwen3TTS", "checkpoint": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice", "revision": "0c0e3051f131929182e2c023b9537f8b1c68adfe", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 8.603621456772089, "latency_p95_s": 13.723505410738287, "rtf": 1.7696765178685818, "peak_vram_mib": 4351.36962890625, "audio_seconds": 5396.08, "clipping_ratio": 0.0, "silence_ratio": 0.2114373210618118, "rms_dbfs": -21.57469666576863, "normalization_id": "whisper_english", "wer": 0.013815624215021352, "cer": 0.0043890971850264835, "mer": 0.013802911159444537, "wil": 0.02513313514949267, "wip": 0.9748668648505073, "word_hits": 11789, "word_substitutions": 137, "word_deletions": 17, "word_insertions": 11, "reference_words": 11943, "char_hits": 66985, "char_substitutions": 116, "char_deletions": 111, "char_insertions": 68, "reference_chars": 67212, "exact_match_rate": 0.8832720588235294, "raw": { "wer": 0.05775745257452575, "cer": 0.014281993401632227, "mer": 0.057737893667456824, "wil": 0.10905054114235402, "wip": 0.890949458857646, "word_hits": 11130, "word_substitutions": 641, "word_deletions": 37, "word_insertions": 4, "reference_words": 11808, "char_hits": 68298, "char_substitutions": 420, "char_deletions": 390, "char_insertions": 177, "reference_chars": 69108, "exact_match_rate": 0.6259191176470589 }, "orthographic": { "wer": 0.016165890816758358, "cer": 0.006269778774867399, "mer": 0.016159052453468697, "wil": 0.029841656027112418, "wip": 0.9701583439728876, "word_hits": 11629, "word_substitutions": 164, "word_deletions": 22, "word_insertions": 5, "reference_words": 11815, "char_hits": 66938, "char_substitutions": 145, "char_deletions": 224, "char_insertions": 53, "reference_chars": 67307, "exact_match_rate": 0.8621323529411765 }, "wer_ci95": [ 0.011347743257994994, 0.016629512899164478 ], "cer_ci95": [ 0.00341322717010673, 0.005637916399275065 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.013815624215021352, "cer": 0.0043890971850264835, "mer": 0.013802911159444537, "wil": 0.02513313514949267, "wip": 0.9748668648505073, "word_hits": 11789, "word_substitutions": 137, "word_deletions": 17, "word_insertions": 11, "reference_words": 11943, "char_hits": 66985, "char_substitutions": 116, "char_deletions": 111, "char_insertions": 68, "reference_chars": 67212, "exact_match_rate": 0.8832720588235294 } }, "utterance_mean_wer": 0.013853437463272021, "utterance_mean_cer": 0.004452845678980064 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-qwen3tts-seedtts_en-000", "result_sha256": "4599ad00909bf5add6e6f27f3f3a6b202f378689ffc19dc13621082b74786d46", "config_sha256": "7b9ad8473b9005027c6cce49cad82993068834966e3004c2ffcafbf1cd8e47d2", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-qwen3tts-seedtts_en-001", "result_sha256": "aae11dcb76378183e8204b2f7b5059c104908944ebc1fc0fa23b326be8e9628b", "config_sha256": "09911adff74beed626eeac78bfc562c2e73a47ebb8b7fed944fcf2e07650c7e5", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-qwen3tts-seedtts_en-002", "result_sha256": "e8ad7fbaf05225d55c4f62640de3ee0bb9ed684fd655cf3c5eced6bc156c1915", "config_sha256": "4a4748f23dfc80cc2112cea980fc062a89a66da439ec50b7f874e9e3e4cf79fa", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-qwen3tts-seedtts_en-003", "result_sha256": "41b9f0863020828fc82e66b3ff4ea0c4cefea8721bb409ec2c439eb023040a20", "config_sha256": "709378115906f653258c3aee307c65cf3bff87a7cc11e61f64ffb4e6b68a7eb9", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-qwen3tts-seedtts_en-004", "result_sha256": "fa8fd67693b1e66539ef66417f47aec996f862c973855ad8eb54a7e8490480a6", "config_sha256": "febf78f198da9c4c966327555b3bc6a04024d8a3868990ad826f659bb19663cf", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-qwen3tts-seedtts_en-005", "result_sha256": "90e1020b7cb7c8cb4677656b4ffe1f6a24caf109603a1017d498c722e1417305", "config_sha256": "d1ec321689f3687c92f553a14efdad49c1bad7c6d21547a1bdc41129c09ba7bb", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "neutts", "name": "NeuTTS", "checkpoint": "neuphonic/neutts-2e", "revision": "412aaab11c6b727c6c0fe2552db305c234e568da", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 6.949139470234513, "latency_p95_s": 9.845434662140903, "rtf": 1.7043660177076607, "peak_vram_mib": 3476.28369140625, "audio_seconds": 4472.06, "clipping_ratio": 4.345555472947041e-06, "silence_ratio": 0.27913515952061047, "rms_dbfs": -19.889727299836053, "normalization_id": "whisper_english", "wer": 0.014736665829356108, "cer": 0.006204249241206927, "mer": 0.014692378328741965, "wil": 0.02428765130115995, "wip": 0.97571234869884, "word_hits": 11803, "word_substitutions": 116, "word_deletions": 24, "word_insertions": 36, "reference_words": 11943, "char_hits": 66985, "char_substitutions": 88, "char_deletions": 139, "char_insertions": 190, "reference_chars": 67212, "exact_match_rate": 0.8887867647058824, "raw": { "wer": 0.05005081300813008, "cer": 0.014687156335011865, "mer": 0.04993662864385298, "wil": 0.09201670417314756, "wip": 0.9079832958268524, "word_hits": 11244, "word_substitutions": 521, "word_deletions": 43, "word_insertions": 27, "reference_words": 11808, "char_hits": 68321, "char_substitutions": 384, "char_deletions": 403, "char_insertions": 228, "reference_chars": 69108, "exact_match_rate": 0.6700367647058824 }, "orthographic": { "wer": 0.017181548878544225, "cer": 0.008126940734247553, "mer": 0.017136586189431032, "wil": 0.029150115444661617, "wip": 0.9708498845553384, "word_hits": 11643, "word_substitutions": 144, "word_deletions": 28, "word_insertions": 31, "reference_words": 11815, "char_hits": 66937, "char_substitutions": 120, "char_deletions": 250, "char_insertions": 177, "reference_chars": 67307, "exact_match_rate": 0.8667279411764706 }, "wer_ci95": [ 0.011031144307612399, 0.019876654385442543 ], "cer_ci95": [ 0.003660288780343977, 0.010057701099493685 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.014736665829356108, "cer": 0.006204249241206927, "mer": 0.014692378328741965, "wil": 0.02428765130115995, "wip": 0.97571234869884, "word_hits": 11803, "word_substitutions": 116, "word_deletions": 24, "word_insertions": 36, "reference_words": 11943, "char_hits": 66985, "char_substitutions": 88, "char_deletions": 139, "char_insertions": 190, "reference_chars": 67212, "exact_match_rate": 0.8887867647058824 } }, "utterance_mean_wer": 0.014267839703068943, "utterance_mean_cer": 0.00575985081832371 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-neutts-seedtts_en-000", "result_sha256": "09f6ab121178bfdfb072b518864adf9dcfaf3af8339e35476b8527897a59b802", "config_sha256": "ecb01ace6d0aea7feab33d45fd4c7193a8558bc094e0fbe3d391cfce74be97e6", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-neutts-seedtts_en-001", "result_sha256": "467a71c8920670b34507cee0635901e1ad62eb4905eae6c0e7d7409374c77184", "config_sha256": "553fb6440c282c0449ef6ea5a19130d097129a5197852beb249529f90c0ea58b", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-neutts-seedtts_en-002", "result_sha256": "d9544ca9cf58e3cb2b73cf4d978ca15328318ecc2c5ed17ce16095abf0163851", "config_sha256": "170601f7b149e88df40a917b173941376a1183df669bdd6d5499949225b241d2", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-neutts-seedtts_en-003", "result_sha256": "e4db1689d24882d7a6e997c30fc11c4dbf5dc39c2c9cb34296a6536456237ceb", "config_sha256": "3e81e2feeb1bbd3b6d2291601c1a0e65c96e5a47e8ca0a112389c7059243dcf4", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-neutts-seedtts_en-004", "result_sha256": "29227d8f008759405cd61d1c6f4c017a4b103ccd62859b3c58ee6c8eac8903b1", "config_sha256": "24b86a31293a044f81135a3d891528f1d80e54f25955514632242cc9928351c4", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-neutts-seedtts_en-005", "result_sha256": "1e18e1acd1f0267eafa0fdf857b19ddd8130246d097099a97a63a36b07ce897a", "config_sha256": "534d12be5a4bef75916059793ff05c64c9f3638391fc05de26f15c0e1a4ec690", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "higgstts", "name": "HiggsTTS", "checkpoint": "bosonai/higgs-tts-2-3b-base", "revision": "d80c511612b3040ff2877ce3d408747df1739f11", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 4.582375276833773, "latency_p95_s": 7.186718510463833, "rtf": 1.171588010392337, "peak_vram_mib": 11947.0888671875, "audio_seconds": 4356.6, "clipping_ratio": 2.2705394611234025e-06, "silence_ratio": 0.2434151965391991, "rms_dbfs": -21.519289781106792, "normalization_id": "whisper_english", "wer": 0.017416059616511763, "cer": 0.006710111289650658, "mer": 0.01738113144480655, "wil": 0.02976327841893811, "wip": 0.9702367215810619, "word_hits": 11759, "word_substitutions": 150, "word_deletions": 34, "word_insertions": 24, "reference_words": 11943, "char_hits": 66901, "char_substitutions": 145, "char_deletions": 166, "char_insertions": 140, "reference_chars": 67212, "exact_match_rate": 0.859375, "raw": { "wer": 0.06317750677506775, "cer": 0.016611680268565146, "mer": 0.06309201623815967, "wil": 0.11675614684675784, "wip": 0.8832438531532422, "word_hits": 11078, "word_substitutions": 673, "word_deletions": 57, "word_insertions": 16, "reference_words": 11808, "char_hits": 68166, "char_substitutions": 505, "char_deletions": 437, "char_insertions": 206, "reference_chars": 69108, "exact_match_rate": 0.5974264705882353 }, "orthographic": { "wer": 0.02031316123571731, "cer": 0.008305228282348047, "mer": 0.02028740490278952, "wil": 0.03552046085441474, "wip": 0.9644795391455853, "word_hits": 11590, "word_substitutions": 183, "word_deletions": 42, "word_insertions": 15, "reference_words": 11815, "char_hits": 66856, "char_substitutions": 177, "char_deletions": 274, "char_insertions": 108, "reference_chars": 67307, "exact_match_rate": 0.8363970588235294 }, "wer_ci95": [ 0.014684263569190567, 0.02052255964339718 ], "cer_ci95": [ 0.005334938979585008, 0.008322318642279253 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.017416059616511763, "cer": 0.006710111289650658, "mer": 0.01738113144480655, "wil": 0.02976327841893811, "wip": 0.9702367215810619, "word_hits": 11759, "word_substitutions": 150, "word_deletions": 34, "word_insertions": 24, "reference_words": 11943, "char_hits": 66901, "char_substitutions": 145, "char_deletions": 166, "char_insertions": 140, "reference_chars": 67212, "exact_match_rate": 0.859375 } }, "utterance_mean_wer": 0.017204365538464803, "utterance_mean_cer": 0.006782952438796437 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-higgstts-seedtts_en-000", "result_sha256": "b349a206a037a08c1840d1ed9aafe8a92beb6ffcad96e74f10d34f7394d10128", "config_sha256": "b14f013cae01241a74f007931f43f3220fd314fb2111a92391c03fa76835c092", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-higgstts-seedtts_en-001", "result_sha256": "d168b4a8fd90f9a76843ce1bb8b1f1d6f202a42ab12c40609b7136ea6a29f167", "config_sha256": "4d3805d0e51d721bf0b31e16310612932f69bb6be22a704b066084b53f5d07b4", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-higgstts-seedtts_en-002", "result_sha256": "332de2c9bd1265c68105cdffc3d48a51dd1e38e4fed5c6af24ec632fd8654f4a", "config_sha256": "72219946666ca8c0a2ee87fd26ff75ae83e565bf080134f2778ca8979d9d8548", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-higgstts-seedtts_en-003", "result_sha256": "8def67f27c34ab7410b377eb4a41ff899583820c2f465c9c09e02d6799abddc3", "config_sha256": "40f4009b67a5c97be8d2e2ce14e21e2deb7b482f2c91ed3b940e346a058fa203", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-higgstts-seedtts_en-004", "result_sha256": "d05f88abbefc019fd4c38a6d76c45fbfcda9dccff102e3823e0bb32df20faccb", "config_sha256": "f91f582d1bc4f6ab1a32af9699072da6a6bc38a9338923d172b8c62fce90cda3", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-higgstts-seedtts_en-005", "result_sha256": "4644bb00894104f10e09d83b2557448ec2a544d678f8b17d233a7603eabed217", "config_sha256": "5858f648b6cba46f94cb1a8aadcb8608bc0cc0a429ee70d35cc7a8db9ad1ea0c", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "inflecttts", "name": "InflectTTS", "checkpoint": "owensong/Inflect-Micro-v2", "revision": "132edf8700da8e0d3fa81cdc0fd8844926fc6582", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.060717109590768814, "latency_p95_s": 0.07416072003543377, "rtf": 0.014407729416794657, "peak_vram_mib": 174.49169921875, "audio_seconds": 4074.2906666666668, "clipping_ratio": 0.0, "silence_ratio": 0.23552280891102917, "rms_dbfs": -23.741855445278556, "normalization_id": "whisper_english", "wer": 0.017583521728208994, "cer": 0.0058918050348152114, "mer": 0.017562933846282512, "wil": 0.03222911364088443, "wip": 0.9677708863591156, "word_hits": 11747, "word_substitutions": 178, "word_deletions": 18, "word_insertions": 14, "reference_words": 11943, "char_hits": 66925, "char_substitutions": 177, "char_deletions": 110, "char_insertions": 109, "reference_chars": 67212, "exact_match_rate": 0.8566176470588235, "raw": { "wer": 0.05157520325203252, "cer": 0.01435434392545002, "mer": 0.051518484053802556, "wil": 0.09641124971765758, "wip": 0.9035887502823424, "word_hits": 11212, "word_substitutions": 557, "word_deletions": 39, "word_insertions": 13, "reference_words": 11808, "char_hits": 68240, "char_substitutions": 478, "char_deletions": 390, "char_insertions": 124, "reference_chars": 69108, "exact_match_rate": 0.6672794117647058 }, "orthographic": { "wer": 0.02073635209479475, "cer": 0.008022939664522263, "mer": 0.020715312420732223, "wil": 0.03831992870492207, "wip": 0.9616800712950779, "word_hits": 11582, "word_substitutions": 212, "word_deletions": 21, "word_insertions": 12, "reference_words": 11815, "char_hits": 66867, "char_substitutions": 207, "char_deletions": 233, "char_insertions": 100, "reference_chars": 67307, "exact_match_rate": 0.8272058823529411 }, "wer_ci95": [ 0.014729798756944202, 0.020587894869992844 ], "cer_ci95": [ 0.004852113065057902, 0.006962616006936535 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.017583521728208994, "cer": 0.0058918050348152114, "mer": 0.017562933846282512, "wil": 0.03222911364088443, "wip": 0.9677708863591156, "word_hits": 11747, "word_substitutions": 178, "word_deletions": 18, "word_insertions": 14, "reference_words": 11943, "char_hits": 66925, "char_substitutions": 177, "char_deletions": 110, "char_insertions": 109, "reference_chars": 67212, "exact_match_rate": 0.8566176470588235 } }, "utterance_mean_wer": 0.017602403723727254, "utterance_mean_cer": 0.006094378628546624 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-inflecttts-seedtts_en-000", "result_sha256": "4e19b3c2ddf61761f6581b6cee3a451da7f5b321e70ad08325f8df80b7e1f13e", "config_sha256": "82ee7ed2fbf3c6dfe030a16513617cf7cf080e577d4c36a74bb14f693d587139", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-inflecttts-seedtts_en-001", "result_sha256": "6a1e178764dea6f643d89fb2d2a29140e29494547b4f4a66a5bab19fde4b6f54", "config_sha256": "46a1d1a0c922127cfe57a465fb8f527093ac2817cfde4a4b54d9ab810fbd60f7", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-inflecttts-seedtts_en-002", "result_sha256": "6d4a8cdb6106384a8e816b845eb902e75dee27cc504e840741b0d3269c62b8a9", "config_sha256": "e728a7e295127e784900965b66d710c2924b304fe450947e38ed024b469cc704", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-inflecttts-seedtts_en-003", "result_sha256": "7ba148fae816861d6adcbf9687fcb26643b46de3cfb427834a6291089e90020d", "config_sha256": "e8e9b2140661b2c737e853be5ee1f10881c8f47fa9f69150445c6fd5e2f5e79e", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-inflecttts-seedtts_en-004", "result_sha256": "37da9feabc214e3a61a854357c23af67bb27e874634cefbafbdb929edce42086", "config_sha256": "69bed90688690c37ad7171aa64e209e8c62b0745fb283a4cfec47f9025a7e492", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-inflecttts-seedtts_en-005", "result_sha256": "395b5646e1bf1a05d07403b036f51cb9dfa0c9ed730bd2fed7405c1db392778a", "config_sha256": "f8d3009b7dd8d09bea032033dfcf6c37a543818aaefbf3284c2ec40fa02bb46a", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "orpheustts", "name": "OrpheusTTS", "checkpoint": "canopylabs/orpheus-3b-0.1-ft", "revision": "4206a56e5a68cf6cf96900a8a78acd3370c02eb6", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 11.744120076298714, "latency_p95_s": 17.74872815031558, "rtf": 2.5830602675349486, "peak_vram_mib": 6409.50244140625, "audio_seconds": 5113.685333333333, "clipping_ratio": 0.0, "silence_ratio": 0.40942533109258156, "rms_dbfs": -27.90337897777544, "normalization_id": "whisper_english", "wer": 0.020011722347818808, "cer": 0.007692078795453193, "mer": 0.019973257563095436, "wil": 0.03503674213176289, "wip": 0.9649632578682371, "word_hits": 11727, "word_substitutions": 183, "word_deletions": 33, "word_insertions": 23, "reference_words": 11943, "char_hits": 66827, "char_substitutions": 211, "char_deletions": 174, "char_insertions": 132, "reference_chars": 67212, "exact_match_rate": 0.8373161764705882, "raw": { "wer": 0.0687669376693767, "cer": 0.018637494935463333, "mer": 0.06868550160717307, "wil": 0.1283068796765916, "wip": 0.8716931203234084, "word_hits": 11010, "word_substitutions": 753, "word_deletions": 45, "word_insertions": 14, "reference_words": 11808, "char_hits": 68037, "char_substitutions": 584, "char_deletions": 487, "char_insertions": 217, "reference_chars": 69108, "exact_match_rate": 0.5854779411764706 }, "orthographic": { "wer": 0.021921286500211596, "cer": 0.00941952545797614, "mer": 0.021891640605189756, "wil": 0.039410306008345386, "wip": 0.9605896939916546, "word_hits": 11572, "word_substitutions": 211, "word_deletions": 32, "word_insertions": 16, "reference_words": 11815, "char_hits": 66782, "char_substitutions": 243, "char_deletions": 282, "char_insertions": 109, "reference_chars": 67307, "exact_match_rate": 0.8161764705882353 }, "wer_ci95": [ 0.016988210857373835, 0.023450519014427323 ], "cer_ci95": [ 0.006083833741794046, 0.009892766606762127 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.020011722347818808, "cer": 0.007692078795453193, "mer": 0.019973257563095436, "wil": 0.03503674213176289, "wip": 0.9649632578682371, "word_hits": 11727, "word_substitutions": 183, "word_deletions": 33, "word_insertions": 23, "reference_words": 11943, "char_hits": 66827, "char_substitutions": 211, "char_deletions": 174, "char_insertions": 132, "reference_chars": 67212, "exact_match_rate": 0.8373161764705882 } }, "utterance_mean_wer": 0.020058611476350446, "utterance_mean_cer": 0.008047379814062864 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-orpheustts-seedtts_en-000", "result_sha256": "efcd17bf6344678ee7c4d2b3682ea15d952d4dd34a4e6234d19baf7cad723cd2", "config_sha256": "37944a31fa1b17edbee3103899242619e547d29fa92f92a98fd2286641a52515", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-orpheustts-seedtts_en-001", "result_sha256": "180a32b2075a6306bb958011cb4fec462b8851cf53ba5a57b19029de02c96566", "config_sha256": "921ea95419e4e033984b7d95c57579f6cf24d85dd61af1012840757ccd68c911", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-orpheustts-seedtts_en-002", "result_sha256": "ca6032f4b214f65e859df599472a2a07eb9dde067d21d665dae3ca718580355a", "config_sha256": "0d9385a2bb0e2ab55a95143746a4f83c320c5c39cb5a45a060f546f36c82335e", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-orpheustts-seedtts_en-003", "result_sha256": "3d880468994baed08f10cd5b17451f972f77012185cf6355660a9207be2eb4f8", "config_sha256": "90e728cedd27613042053ecfd5904a1226069a658c98910b3c06f24df0448ec4", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-orpheustts-seedtts_en-004", "result_sha256": "2424142ad0d16121410b1154b83cae0114be3263748af6966e1f92aab1c8ab0c", "config_sha256": "63f54df5e03b4de95bfdfde249e5b5dff57d6e0c8e2a853534ad19728ad1f6df", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-orpheustts-seedtts_en-005", "result_sha256": "4f1dafe28af00d135e08df7167c69c6cc4ee6f19d6e8e236fab53bcbaacbe681", "config_sha256": "f3e98fa2c7bc4350459ac9a9c42b79c0111d8a83c0ce2e56b1cba436193e2507", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "zonos", "name": "Zonos", "checkpoint": "Zyphra/Zonos-v0.1-transformer", "revision": "9d8331fc49cb5ba8aad2bb56cafd809c66598f4e", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 6.9678456503897905, "latency_p95_s": 10.227166134119033, "rtf": 1.7680858104657158, "peak_vram_mib": 4144.82080078125, "audio_seconds": 4331.996009070294, "clipping_ratio": 1.1080583572800664e-07, "silence_ratio": 0.26132722105228, "rms_dbfs": -23.673586565392633, "normalization_id": "whisper_english", "wer": 0.02302604035836892, "cer": 0.0096411355115158, "mer": 0.022951093306626605, "wil": 0.037599506467079435, "wip": 0.9624004935329206, "word_hits": 11707, "word_substitutions": 178, "word_deletions": 58, "word_insertions": 39, "reference_words": 11943, "char_hits": 66756, "char_substitutions": 181, "char_deletions": 275, "char_insertions": 192, "reference_chars": 67212, "exact_match_rate": 0.8023897058823529, "raw": { "wer": 0.07173102981029811, "cer": 0.02076460033570643, "mer": 0.0715130023640662, "wil": 0.13006869071599914, "wip": 0.8699313092840009, "word_hits": 10997, "word_substitutions": 740, "word_deletions": 71, "word_insertions": 36, "reference_words": 11808, "char_hits": 67927, "char_substitutions": 575, "char_deletions": 606, "char_insertions": 254, "reference_chars": 69108, "exact_match_rate": 0.5477941176470589 }, "orthographic": { "wer": 0.026661024121878967, "cer": 0.0118561219486829, "mer": 0.026580035440047254, "wil": 0.04489202747966681, "wip": 0.9551079725203332, "word_hits": 11536, "word_substitutions": 221, "word_deletions": 58, "word_insertions": 36, "reference_words": 11815, "char_hits": 66705, "char_substitutions": 220, "char_deletions": 382, "char_insertions": 196, "reference_chars": 67307, "exact_match_rate": 0.7775735294117647 }, "wer_ci95": [ 0.02007390075144153, 0.026153331156134465 ], "cer_ci95": [ 0.008174096745526271, 0.01130165207207019 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.02302604035836892, "cer": 0.0096411355115158, "mer": 0.022951093306626605, "wil": 0.037599506467079435, "wip": 0.9624004935329206, "word_hits": 11707, "word_substitutions": 178, "word_deletions": 58, "word_insertions": 39, "reference_words": 11943, "char_hits": 66756, "char_substitutions": 181, "char_deletions": 275, "char_insertions": 192, "reference_chars": 67212, "exact_match_rate": 0.8023897058823529 } }, "utterance_mean_wer": 0.023355699436872036, "utterance_mean_cer": 0.010020021987216247 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-zonos-seedtts_en-000", "result_sha256": "14c30b42419a188275ad5bd46f4391492de071a491406ed671ca512d1214460b", "config_sha256": "9043d82e15039486d8013fd004ff89c5c0e51ac3acb1781782b1e03847bae6e2", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-zonos-seedtts_en-001", "result_sha256": "34be0fdeedcae3dedf60e22b8abca0453faf690283829d009f97868c2f9d74a0", "config_sha256": "e8e5dcb61e420c61d80adb538db746fe07871c4a747a45ba0cf171a5f0a88023", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-zonos-seedtts_en-002", "result_sha256": "04b0c65d49442f53a51a41d98424be71b573857dedbd95870f4c6da2eb8be820", "config_sha256": "fe4c23121608de46df3f8d6ca5982bf20490fb17b0db83a690fc2accaec6b053", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-zonos-seedtts_en-003", "result_sha256": "f605e25db2c797b0f364102427f39abab1d356b9f59a6c7086114754f26e18a2", "config_sha256": "f2e4e73dfd2a09ff40caa5c7e4bbd01d87b03e71a78722f6f4e8d9c112bd64eb", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-zonos-seedtts_en-004", "result_sha256": "90ef13624288319ca782f5808bb89ee5afa6e0cd80d6f0d6049349f89d6a551c", "config_sha256": "1e64fe23a5a736e28e492aee7c6de968c1510986960ff97ef13f69cd7f31e9ed", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-zonos-seedtts_en-005", "result_sha256": "0f07e10db273655d9d6d57456381b41740ac1536f478e8f8c1aaec1432adf62b", "config_sha256": "db5980cd20c82c598831546388dc85828d867b9c83d0e7ef5b734b2294db7498", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "gptsovits", "name": "GPTSoVITS", "checkpoint": "lj1995/GPT-SoVITS", "revision": "336b2ec4e8d4ac74740798dd40af44e74659ecaf", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 1.066016722470522, "latency_p95_s": 1.7044374926015722, "rtf": 0.3222476706943061, "peak_vram_mib": 764.4111328125, "audio_seconds": 3679.6, "clipping_ratio": 0.0, "silence_ratio": 0.15031361795966175, "rms_dbfs": -21.53940639823217, "normalization_id": "whisper_english", "wer": 0.02637528259231349, "cer": 0.008703802892340653, "mer": 0.02626532143750521, "wil": 0.04524414603704274, "wip": 0.9547558539629573, "word_hits": 11678, "word_substitutions": 232, "word_deletions": 33, "word_insertions": 50, "reference_words": 11943, "char_hits": 66819, "char_substitutions": 238, "char_deletions": 155, "char_insertions": 192, "reference_chars": 67212, "exact_match_rate": 0.8226102941176471, "raw": { "wer": 0.06444783197831978, "cer": 0.018333622735428604, "mer": 0.06427364864864865, "wil": 0.11854431783633534, "wip": 0.8814556821636647, "word_hits": 11079, "word_substitutions": 682, "word_deletions": 47, "word_insertions": 32, "reference_words": 11808, "char_hits": 68051, "char_substitutions": 606, "char_deletions": 451, "char_insertions": 210, "reference_chars": 69108, "exact_match_rate": 0.6047794117647058 }, "orthographic": { "wer": 0.02852306390181972, "cer": 0.010608109111979437, "mer": 0.028426824124841838, "wil": 0.05012555211084746, "wip": 0.9498744478891525, "word_hits": 11518, "word_substitutions": 263, "word_deletions": 34, "word_insertions": 40, "reference_words": 11815, "char_hits": 66764, "char_substitutions": 270, "char_deletions": 273, "char_insertions": 171, "reference_chars": 67307, "exact_match_rate": 0.8005514705882353 }, "wer_ci95": [ 0.022651802065312383, 0.030441862466967787 ], "cer_ci95": [ 0.007285552893791007, 0.010238613992923822 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.02637528259231349, "cer": 0.008703802892340653, "mer": 0.02626532143750521, "wil": 0.04524414603704274, "wip": 0.9547558539629573, "word_hits": 11678, "word_substitutions": 232, "word_deletions": 33, "word_insertions": 50, "reference_words": 11943, "char_hits": 66819, "char_substitutions": 238, "char_deletions": 155, "char_insertions": 192, "reference_chars": 67212, "exact_match_rate": 0.8226102941176471 } }, "utterance_mean_wer": 0.02771551747884468, "utterance_mean_cer": 0.009832378998327021 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-gptsovits-seedtts_en-000", "result_sha256": "68c67a56f38d0ae45b02230c9064b0d0e85094da3ef9e8259656829365521b30", "config_sha256": "932901f4efbcc0c8c6eafbe4932f138ac131748b48b6a5263719779134e3a4ea", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-gptsovits-seedtts_en-001", "result_sha256": "df73320b1a6164e64986fac28235db1a1aff3c714bd708c539ba2c21cbe59b75", "config_sha256": "68e36877407486cdb5b4c386a3d3be6bd3bc66e48fc4a8c6da869948cd1b95be", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-gptsovits-seedtts_en-002", "result_sha256": "c0966884e65f54ce8755e2cb1dc8d0698e73c2b935230637036444639a98f1a4", "config_sha256": "d18e78970d7ffdfec4dc3ffaa0e28913b79d9b2ed9c791e2ca129d44c60153f4", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-gptsovits-seedtts_en-003", "result_sha256": "53470ad72590edc8ac0bcc70ef5f86494bf8b002861777d587dbda4752916660", "config_sha256": "17ef2a9cc9762a5498820a4fc98ec3a4a967ebb7641056ef8b7c5d9eac2eb98c", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-gptsovits-seedtts_en-004", "result_sha256": "022a342fabfc883c717a98b26a233703167c98fb8216ff668d7609c31df31401", "config_sha256": "7460e9bfdcc44590575be8d904ac302c0d76a4578870624423c630862e923b9e", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-gptsovits-seedtts_en-005", "result_sha256": "0b4959029afda72e4429ccb580101d921cbd3c92b142978fc80ee2aae3d0bcbb", "config_sha256": "eaa8fb7e9474c81f7d33bc99a8459388cec6fb9806b44c3be6cd655f2ce8aef0", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "melotts", "name": "MeloTTS", "checkpoint": "EN", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.1015011165291071, "latency_p95_s": 0.11808984335511923, "rtf": 0.019975049763602603, "peak_vram_mib": 506.787109375, "audio_seconds": 4986.566530612245, "clipping_ratio": 0.0, "silence_ratio": 0.3701696886986826, "rms_dbfs": -26.93682087807902, "normalization_id": "whisper_english", "wer": 0.02637528259231349, "cer": 0.01065285960840326, "mer": 0.026328986960882646, "wil": 0.048229403790975844, "wip": 0.9517705962090242, "word_hits": 11649, "word_substitutions": 268, "word_deletions": 26, "word_insertions": 21, "reference_words": 11943, "char_hits": 66675, "char_substitutions": 354, "char_deletions": 183, "char_insertions": 179, "reference_chars": 67212, "exact_match_rate": 0.7766544117647058, "raw": { "wer": 0.0725779132791328, "cer": 0.021965619031081785, "mer": 0.07247357293868922, "wil": 0.1353118233270264, "wip": 0.8646881766729736, "word_hits": 10968, "word_substitutions": 797, "word_deletions": 43, "word_insertions": 17, "reference_words": 11808, "char_hits": 67803, "char_substitutions": 704, "char_deletions": 601, "char_insertions": 213, "reference_chars": 69108, "exact_match_rate": 0.5422794117647058 }, "orthographic": { "wer": 0.030977570884468897, "cer": 0.013772713090763219, "mer": 0.030933062880324543, "wil": 0.05708761850984678, "wip": 0.9429123814901532, "word_hits": 11466, "word_substitutions": 318, "word_deletions": 31, "word_insertions": 17, "reference_words": 11815, "char_hits": 66548, "char_substitutions": 405, "char_deletions": 354, "char_insertions": 168, "reference_chars": 67307, "exact_match_rate": 0.7444852941176471 }, "wer_ci95": [ 0.02316930251848474, 0.029679677277896818 ], "cer_ci95": [ 0.009173332758245023, 0.012222008404797419 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.02637528259231349, "cer": 0.01065285960840326, "mer": 0.026328986960882646, "wil": 0.048229403790975844, "wip": 0.9517705962090242, "word_hits": 11649, "word_substitutions": 268, "word_deletions": 26, "word_insertions": 21, "reference_words": 11943, "char_hits": 66675, "char_substitutions": 354, "char_deletions": 183, "char_insertions": 179, "reference_chars": 67212, "exact_match_rate": 0.7766544117647058 } }, "utterance_mean_wer": 0.02676533790963938, "utterance_mean_cer": 0.01089498176697487 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-melotts-seedtts_en-000", "result_sha256": "92660fa12cd986a61b233098b2bd145a6f7a70ff2f529c9969ba4a9b6937e97a", "config_sha256": "4446c02f56bb5a8fa50bdf045b9d7fbcca62b13824815680867c2a756224aaf8", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-melotts-seedtts_en-001", "result_sha256": "529d42b0571d7cd7bbd48735394c32083d2a9d264f3af6798f06c97379729230", "config_sha256": "38633d6031f3222dfacfe1b9cdbd99a49dde3aae701e89c066807845b28a9484", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-melotts-seedtts_en-002", "result_sha256": "402d59bbf83f22b26c0cffe5069e37204607e6e788f0eacf8c2614c8e5af20c8", "config_sha256": "2980c63d6f2bff670d524b932b1d1a58b58f2256398442688e2ea28d11e3701e", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-melotts-seedtts_en-003", "result_sha256": "bdac8ed487435a29354e8bf852372d28701d8ef72a8fde7b6d60c14bb0879674", "config_sha256": "34f5259091972e75161f512219f7cbb2e6323e8b9ca3497c8190a2bac4110f2d", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-melotts-seedtts_en-004", "result_sha256": "cce1f7b26b118f7898e91c5153f5220acd417e2ce775b10a044819514612da57", "config_sha256": "72bfda633f01250a6d580c80cd57e536f26db1c6651b7b9bc8f780adbfb7f5df", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-melotts-seedtts_en-005", "result_sha256": "12aecf33f19836eef9e0e13676adb49ef77e35b183bf63bb02207121409198ac", "config_sha256": "a176528f50b490e0111404461fd621473c38c5bade9a9cdd604d1ccbbeece816", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "parlertts", "name": "ParlerTTS", "checkpoint": "parler-tts/parler-tts-mini-v1", "revision": "0392b9451a601e528fd863bbb0598431fee810d9", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 6.555586036294699, "latency_p95_s": 11.28402764480561, "rtf": 1.8774146532842886, "peak_vram_mib": 4507.4521484375, "audio_seconds": 4018.3873015873014, "clipping_ratio": 7.417982043023822e-09, "silence_ratio": 0.1515094306108054, "rms_dbfs": -18.799491891228392, "normalization_id": "whisper_english", "wer": 0.026542744704010718, "cer": 0.0144617032672737, "mer": 0.026438698915763136, "wil": 0.04502352105370688, "wip": 0.9549764789462931, "word_hits": 11673, "word_substitutions": 227, "word_deletions": 43, "word_insertions": 47, "reference_words": 11943, "char_hits": 66504, "char_substitutions": 357, "char_deletions": 351, "char_insertions": 264, "reference_chars": 67212, "exact_match_rate": 0.8079044117647058, "raw": { "wer": 0.07283197831978319, "cer": 0.024743879145685016, "mer": 0.0725799645539708, "wil": 0.13266002542244915, "wip": 0.8673399745775509, "word_hits": 10989, "word_substitutions": 761, "word_deletions": 58, "word_insertions": 41, "reference_words": 11808, "char_hits": 67761, "char_substitutions": 705, "char_deletions": 642, "char_insertions": 363, "reference_chars": 69108, "exact_match_rate": 0.5615808823529411 }, "orthographic": { "wer": 0.02928480744815912, "cer": 0.016268738764170145, "mer": 0.02917369308600337, "wil": 0.050383522088299326, "wip": 0.9496164779117007, "word_hits": 11514, "word_substitutions": 257, "word_deletions": 44, "word_insertions": 45, "reference_words": 11815, "char_hits": 66469, "char_substitutions": 389, "char_deletions": 449, "char_insertions": 257, "reference_chars": 67307, "exact_match_rate": 0.7830882352941176 }, "wer_ci95": [ 0.0227290026732326, 0.03095461490670336 ], "cer_ci95": [ 0.012000777770688552, 0.017373967449886223 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.026542744704010718, "cer": 0.0144617032672737, "mer": 0.026438698915763136, "wil": 0.04502352105370688, "wip": 0.9549764789462931, "word_hits": 11673, "word_substitutions": 227, "word_deletions": 43, "word_insertions": 47, "reference_words": 11943, "char_hits": 66504, "char_substitutions": 357, "char_deletions": 351, "char_insertions": 264, "reference_chars": 67212, "exact_match_rate": 0.8079044117647058 } }, "utterance_mean_wer": 0.027006843773840338, "utterance_mean_cer": 0.014403632229321195 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-parlertts-seedtts_en-000", "result_sha256": "cba192bb1c70a538cf56f263714dd81dfc2f9782bcf10601fa44ac734ad02227", "config_sha256": "6887e49a50bb7fd8a353f1e308edd8e3233e1b28bbc0f2b0405d4ff9f74ce990", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-parlertts-seedtts_en-001", "result_sha256": "9bc6630c0d6fa82bd6d45fa0b1fb43d471a8bc2025ab01e1ae6191bc0c7d6048", "config_sha256": "0b45a8e09226715c14a81f757647c0b8b4a40cdc7e2b0c087eb1074e64d34e89", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-parlertts-seedtts_en-002", "result_sha256": "a48799ed03e57f42890debcad36886a4324d72a65850ae0c8ab1746477b147be", "config_sha256": "c4217889669447ffae4b49f8265b06ac2164961075d2e5a8209e235305187f72", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-parlertts-seedtts_en-003", "result_sha256": "3d0ba5029038d918160a861066914b4e3bf1e5b2468aabef3f6632d5bb3e8a5c", "config_sha256": "c2b48aa3a3e962a87e1b6f9e16fcdbd98423c87329bc789baf018491ddc90019", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-parlertts-seedtts_en-004", "result_sha256": "ba631ccca4d49914ca782fd258c88044384294fd4ec4f6e165bff74f67195f6a", "config_sha256": "d9eee540d76d7bc7dbd60b8ab2a020ca240a5f09c97dbe2c48601ee15c6ff05c", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-parlertts-seedtts_en-005", "result_sha256": "537cb30b41a8daa1dcfac07274b901eb6b3f445e61ab763a0ab11f080e1ffed8", "config_sha256": "39d96969c95fcdb384e5bfb682b12616acbfd405142a725e8a33c8837d6ece34", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "csm", "name": "CSM", "checkpoint": "sesame/csm-1b", "revision": "c92a71e1c419772e25be7dc14d952c2521a740ab", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 8.784898072481155, "latency_p95_s": 15.126542358100414, "rtf": 2.2531292765703044, "peak_vram_mib": 4330.97998046875, "audio_seconds": 4515.44, "clipping_ratio": 3.525773558828079e-05, "silence_ratio": 0.3169689076414828, "rms_dbfs": -26.242882987863332, "normalization_id": "whisper_english", "wer": 0.026710206815707946, "cer": 0.014878295542462656, "mer": 0.026462048942347573, "wil": 0.04070971618598751, "wip": 0.9592902838140125, "word_hits": 11736, "word_substitutions": 174, "word_deletions": 33, "word_insertions": 112, "reference_words": 11943, "char_hits": 66835, "char_substitutions": 218, "char_deletions": 159, "char_insertions": 623, "reference_chars": 67212, "exact_match_rate": 0.8088235294117647, "raw": { "wer": 0.0725779132791328, "cer": 0.025221392602882444, "mer": 0.07194425789120215, "wil": 0.12761134062052848, "wip": 0.8723886593794715, "word_hits": 11055, "word_substitutions": 705, "word_deletions": 48, "word_insertions": 104, "reference_words": 11808, "char_hits": 68042, "char_substitutions": 667, "char_deletions": 399, "char_insertions": 677, "reference_chars": 69108, "exact_match_rate": 0.5790441176470589 }, "orthographic": { "wer": 0.02996191282268303, "cer": 0.016981888956572124, "mer": 0.029680556720046953, "wil": 0.04651722181056417, "wip": 0.9534827781894358, "word_hits": 11573, "word_substitutions": 204, "word_deletions": 38, "word_insertions": 112, "reference_words": 11815, "char_hits": 66783, "char_substitutions": 247, "char_deletions": 277, "char_insertions": 619, "reference_chars": 67307, "exact_match_rate": 0.7849264705882353 }, "wer_ci95": [ 0.02256984690648647, 0.03114456456487128 ], "cer_ci95": [ 0.012244555826613683, 0.017740773268843477 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.026710206815707946, "cer": 0.014878295542462656, "mer": 0.026462048942347573, "wil": 0.04070971618598751, "wip": 0.9592902838140125, "word_hits": 11736, "word_substitutions": 174, "word_deletions": 33, "word_insertions": 112, "reference_words": 11943, "char_hits": 66835, "char_substitutions": 218, "char_deletions": 159, "char_insertions": 623, "reference_chars": 67212, "exact_match_rate": 0.8088235294117647 } }, "utterance_mean_wer": 0.027264451475091614, "utterance_mean_cer": 0.015297082046186216 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-csm-seedtts_en-000", "result_sha256": "4e96a39da10528209bbe2bede75660e6360e7628347d85d07b2a02d8883d7f86", "config_sha256": "82642982a78a2f0fc644983e208784de3543c83bbd26e7a47608313cddd41f45", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-csm-seedtts_en-001", "result_sha256": "36d9fb5aabbefe3427b127fdf8bc7eedebbb0bbcc448b9b5c4680cbf3e4db544", "config_sha256": "383774f1ef9eae9762b2cfdf3421824ec0d0a4a5504a1c06ea5df7e3697ad58f", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-csm-seedtts_en-002", "result_sha256": "831845e20ce64a704476c926f0ef9039368f5cba3c57baaee21fc34ef51e072e", "config_sha256": "0585db33e83056ced5ff539df45752f83ae30747b7256dcbd6184446c6833c4d", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-csm-seedtts_en-003", "result_sha256": "7e71d723687de7f52326c82e4ee765cabed5558fcd43c643df5453b052096d95", "config_sha256": "9787da2292c6fe5fe247931f59d30154ff63855455cd343deabb079be7192e0a", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-csm-seedtts_en-004", "result_sha256": "f239cca38dd2f2209e320cdfe2f89a029c3fbc7383158307b6b1527ca114e89f", "config_sha256": "bd9d6269b66fecfe72057d0ee11120669ecd081d204fffe6e5920e38694234f6", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-csm-seedtts_en-005", "result_sha256": "941298803a4434653dba5b286663fbdb3d3e933f855a8daa264c4544b81f3803", "config_sha256": "34aff904635b31cbab62df1df8abf4e0c621655f7aef78a88f59a8dc77348b2e", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "voxcpm", "name": "VoxCPM", "checkpoint": "openbmb/VoxCPM2", "revision": "bffb3df5a29440629464e5e839f4d214c8714c3d", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 3.0798537097871304, "latency_p95_s": 4.482512011565265, "rtf": 0.8742893887299773, "peak_vram_mib": 5568.4033203125, "audio_seconds": 3915.68, "clipping_ratio": 0.0, "silence_ratio": 0.25207125031657623, "rms_dbfs": -19.995685779135187, "normalization_id": "whisper_english", "wer": 0.0334924223394457, "cer": 0.02599238231268226, "mer": 0.032706459525756335, "wil": 0.04076054667222251, "wip": 0.9592394533277775, "word_hits": 11830, "word_substitutions": 99, "word_deletions": 14, "word_insertions": 287, "reference_words": 11943, "char_hits": 67067, "char_substitutions": 74, "char_deletions": 71, "char_insertions": 1602, "reference_chars": 67212, "exact_match_rate": 0.8363970588235294, "raw": { "wer": 0.08053861788617886, "cer": 0.036855356832783466, "mer": 0.07870561946536456, "wil": 0.12899821213333718, "wip": 0.8710017878666628, "word_hits": 11132, "word_substitutions": 642, "word_deletions": 34, "word_insertions": 275, "reference_words": 11808, "char_hits": 68301, "char_substitutions": 461, "char_deletions": 346, "char_insertions": 1740, "reference_chars": 69108, "exact_match_rate": 0.5753676470588235 }, "orthographic": { "wer": 0.03554803216250529, "cer": 0.027530568885851397, "mer": 0.034736580927962946, "wil": 0.04515860053579879, "wip": 0.9548413994642012, "word_hits": 11671, "word_substitutions": 127, "word_deletions": 17, "word_insertions": 276, "reference_words": 11815, "char_hits": 67030, "char_substitutions": 108, "char_deletions": 169, "char_insertions": 1576, "reference_chars": 67307, "exact_match_rate": 0.8143382352941176 }, "wer_ci95": [ 0.027210668207721767, 0.04040970866798127 ], "cer_ci95": [ 0.020480165206463754, 0.03256538243822571 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.0334924223394457, "cer": 0.02599238231268226, "mer": 0.032706459525756335, "wil": 0.04076054667222251, "wip": 0.9592394533277775, "word_hits": 11830, "word_substitutions": 99, "word_deletions": 14, "word_insertions": 287, "reference_words": 11943, "char_hits": 67067, "char_substitutions": 74, "char_deletions": 71, "char_insertions": 1602, "reference_chars": 67212, "exact_match_rate": 0.8363970588235294 } }, "utterance_mean_wer": 0.04057948791404673, "utterance_mean_cer": 0.03500154595326482 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-voxcpm-seedtts_en-000", "result_sha256": "524e67d1351d7ddda53a1ad9ba758b158273f9c028f5452efb05a0ec5e5e54db", "config_sha256": "97eb7924ba5c71b0aac9999b16d8b1cc3490e2c3b9b892a625181c5125f8dc81", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-voxcpm-seedtts_en-001", "result_sha256": "6a637f35984708ce9bdd27db7afd8139663d13e5052adf521512def779c32257", "config_sha256": "07ba7299557ad8a7839bc764310792df7aebecb33da854e71ea9c9c8eb0cbf4f", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-voxcpm-seedtts_en-002", "result_sha256": "02c86ae2a9afe1214b842c97a3cd285efa420d41e36501648a24fc96e67a3ff2", "config_sha256": "3bad1426059155237779c936202a255d8436aa6dcccf6bd632ad63a0e47927cd", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-voxcpm-seedtts_en-003", "result_sha256": "6bc871dbc544063c45d54274c9bad2108d276f39fe2522d253dfe25f84fd7613", "config_sha256": "6054bf5f6889278d6bf8321647c05dd4db7db2c56f099425a8e59c29fce31332", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-voxcpm-seedtts_en-004", "result_sha256": "a19f328625e96edc8532ca53c94a03902517bd03f871814716dadd7d8f2258e6", "config_sha256": "e3f11c6bf0a55608c906ead083a7c9a37898e8503f5d0fea98c2f89a3159864f", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-voxcpm-seedtts_en-005", "result_sha256": "699d0f81088c6356aa84b4df14b41094d4d907de101b06544b91c0b378713acf", "config_sha256": "29515a7d0dcb419f6f97dece86f7d1ad662c0963ac711746ab217a50a611aab9", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "openvoice", "name": "OpenVoice", "checkpoint": "myshell-ai/OpenVoiceV2", "revision": "f36e7edfe1684461a8343844af60babc2efbb727", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.18259630538523197, "latency_p95_s": 0.22698942646384238, "rtf": 0.041566943720588286, "peak_vram_mib": 752.9150390625, "audio_seconds": 4986.566530612245, "clipping_ratio": 0.0, "silence_ratio": 0.3955355348300485, "rms_dbfs": -27.237915118797478, "normalization_id": "whisper_english", "wer": 0.03684166457339027, "cer": 0.015904897934892578, "mer": 0.03674014696058784, "wil": 0.06683946355663117, "wip": 0.9331605364433688, "word_hits": 11536, "word_substitutions": 372, "word_deletions": 35, "word_insertions": 33, "reference_words": 11943, "char_hits": 66378, "char_substitutions": 571, "char_deletions": 263, "char_insertions": 235, "reference_chars": 67212, "exact_match_rate": 0.7205882352941176, "raw": { "wer": 0.08773712737127372, "cer": 0.02773919083174162, "mer": 0.08754436369781984, "wil": 0.16176650401902992, "wip": 0.8382334959809701, "word_hits": 10798, "word_substitutions": 956, "word_deletions": 54, "word_insertions": 26, "reference_words": 11808, "char_hits": 67451, "char_substitutions": 984, "char_deletions": 673, "char_insertions": 260, "reference_chars": 69108, "exact_match_rate": 0.5 }, "orthographic": { "wer": 0.04054168429961913, "cer": 0.018185329906250464, "mer": 0.04044924843776389, "wil": 0.07418740113058353, "wip": 0.9258125988694165, "word_hits": 11363, "word_substitutions": 414, "word_deletions": 38, "word_insertions": 27, "reference_words": 11815, "char_hits": 66298, "char_substitutions": 614, "char_deletions": 395, "char_insertions": 215, "reference_chars": 67307, "exact_match_rate": 0.6966911764705882 }, "wer_ci95": [ 0.03259408128993721, 0.0412924532698379 ], "cer_ci95": [ 0.013940913785427172, 0.017979386205271203 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.03684166457339027, "cer": 0.015904897934892578, "mer": 0.03674014696058784, "wil": 0.06683946355663117, "wip": 0.9331605364433688, "word_hits": 11536, "word_substitutions": 372, "word_deletions": 35, "word_insertions": 33, "reference_words": 11943, "char_hits": 66378, "char_substitutions": 571, "char_deletions": 263, "char_insertions": 235, "reference_chars": 67212, "exact_match_rate": 0.7205882352941176 } }, "utterance_mean_wer": 0.039472592478647844, "utterance_mean_cer": 0.01727688301463179 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-openvoice-seedtts_en-000", "result_sha256": "12fe9f549fe51b35660a190bff89e8a22e4d5315d403ff249e89b654fd797d05", "config_sha256": "d2a88f0f79053fdc3ef4db73a98f55f11901c4a93d577587042873aa49eb7ffa", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-openvoice-seedtts_en-001", "result_sha256": "9917c8c804066517031a856dca9fb84754c4cb297cf496570e212d52e517e913", "config_sha256": "1666e3d3557fa888aa6620e0b29915f22950b21b214ed0e0b7edc636b73266fc", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-openvoice-seedtts_en-002", "result_sha256": "0dfe16d7980aacc836d1ed6c106bce434f8ee7ba792dd31854ba70a60af15f17", "config_sha256": "9f9832a14177aaf0f0330fad21f4375fda82e0a66a7afa373eeebe9748d5547c", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-openvoice-seedtts_en-003", "result_sha256": "25cb18c7a3dcf6307d63f4259a868df51924e2dd6d5956fb9dd1b9849d5ecece", "config_sha256": "8a6bbf0de5e90976d014d306270aea3cb56aa8d3a4766c905a83640f79bf6941", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-openvoice-seedtts_en-004", "result_sha256": "ce8a896c607ddc8b3cf76cda2a6d3e9b2acc41a64d8e4ffc627ac940d9b0d67f", "config_sha256": "0b2e652b4582dd88e33db5a4fc80b41e4fc2341ade95df628c9c1f01927601ac", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-openvoice-seedtts_en-005", "result_sha256": "b02fa100d1fc15050b5a8bdae4da061766b0ac52f1158df30d022237f62e9378", "config_sha256": "393c8041a07e33460a8be90de883740f682e6c30af5abbb914bacdc90f72c9fe", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "vits", "name": "Vits", "checkpoint": "facebook/mms-tts-eng", "revision": "c71de0fe7204c83f1c10820a7d696d0b450048ba", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 0.1107128206640482, "latency_p95_s": 0.3603286813944578, "rtf": 0.036346979152729886, "peak_vram_mib": 161.82177734375, "audio_seconds": 4713.184, "clipping_ratio": 0.0, "silence_ratio": 0.24361948208129203, "rms_dbfs": -18.456575731465676, "normalization_id": "whisper_english", "wer": 0.062295905551369005, "cer": 0.02673629708980539, "mer": 0.061881393994843215, "wil": 0.10974369514421811, "wip": 0.8902563048557819, "word_hits": 11279, "word_substitutions": 606, "word_deletions": 58, "word_insertions": 80, "reference_words": 11943, "char_hits": 65855, "char_substitutions": 899, "char_deletions": 458, "char_insertions": 440, "reference_chars": 67212, "exact_match_rate": 0.6084558823529411, "raw": { "wer": 0.11610772357723577, "cer": 0.04038606239509174, "mer": 0.11547207950812768, "wil": 0.20850372907169457, "wip": 0.7914962709283054, "word_hits": 10502, "word_substitutions": 1234, "word_deletions": 72, "word_insertions": 65, "reference_words": 11808, "char_hits": 66861, "char_substitutions": 1398, "char_deletions": 849, "char_insertions": 544, "reference_chars": 69108, "exact_match_rate": 0.40349264705882354 }, "orthographic": { "wer": 0.06440964875158696, "cer": 0.028110003417178005, "mer": 0.06401951711954236, "wil": 0.11450477370162093, "wip": 0.8854952262983791, "word_hits": 11126, "word_substitutions": 634, "word_deletions": 55, "word_insertions": 72, "reference_words": 11815, "char_hits": 65827, "char_substitutions": 925, "char_deletions": 555, "char_insertions": 412, "reference_chars": 67307, "exact_match_rate": 0.5909926470588235 }, "wer_ci95": [ 0.0568077628669862, 0.06791827951441402 ], "cer_ci95": [ 0.024251829595567223, 0.02939332583322282 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.062295905551369005, "cer": 0.02673629708980539, "mer": 0.061881393994843215, "wil": 0.10974369514421811, "wip": 0.8902563048557819, "word_hits": 11279, "word_substitutions": 606, "word_deletions": 58, "word_insertions": 80, "reference_words": 11943, "char_hits": 65855, "char_substitutions": 899, "char_deletions": 458, "char_insertions": 440, "reference_chars": 67212, "exact_match_rate": 0.6084558823529411 } }, "utterance_mean_wer": 0.0668014646232554, "utterance_mean_cer": 0.029005364603199517 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-vits-seedtts_en-000", "result_sha256": "19a41482d06d3988280a966bdee26af4668ab61d80e353aef1733d23f3f7931e", "config_sha256": "4af11cee32d0b711eef730ecb9f8dd3226fcb99475df1c87d3dc1760af750625", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-vits-seedtts_en-001", "result_sha256": "7bdd210177a8dd64da450340311a2bbbaf7e17779f75d18d13c77a0600e0a526", "config_sha256": "1dbc8736f5cd6294c1cc4bf8f00691673ba680312216c046ffc6e75a9600e855", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-vits-seedtts_en-002", "result_sha256": "fc3881027e09ebb29e9d83c26a98d62dad6e1a01046953723f20330f1ee5df82", "config_sha256": "b16351380f41ce8826562ffc18448359997f2042dfbdfcf695a42457e9758fec", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-vits-seedtts_en-003", "result_sha256": "e57a4a69ed7f81f6ce34a42ace0e06043f597e19274e74c8d9507f4a417d8c25", "config_sha256": "8d295e6cd39574dc94e0ee293c9919d550cf1906ffb97961b43d03b548008a62", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-vits-seedtts_en-004", "result_sha256": "2d1c681b388d52d3a7fe54c66fd85cdec1fcf3e150d21717aa9bc9825b2d11a2", "config_sha256": "ef7080c9aad067b0438fe2a9156cedb06e0535dcfed37e0778506aa3d0efaf8e", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-vits-seedtts_en-005", "result_sha256": "f06106fbbf942de2360d317b1c2b2767132e20105e1399bff3abe406619ee09c", "config_sha256": "d3dc0ecbe985fef6bcf388c4fdf8c7376c94f9088f65c2f4ad680dc5a57d65fb", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "bark", "name": "Bark", "checkpoint": "suno/bark-small", "revision": "1dbd7a128513b8ae4a4e2130fed57b7ac9da5bcd", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 7.324050920084119, "latency_p95_s": 17.736357633210712, "rtf": 1.3509386013124312, "peak_vram_mib": 1866.55224609375, "audio_seconds": 6735.826666666667, "clipping_ratio": 4.311951581619864e-05, "silence_ratio": 0.3688515404183891, "rms_dbfs": -25.216558823343817, "normalization_id": "whisper_english", "wer": 0.07736749560411957, "cer": 0.049648872225197885, "mer": 0.07522592200602458, "wil": 0.11118412348963358, "wip": 0.8888158765103664, "word_hits": 11359, "word_substitutions": 456, "word_deletions": 128, "word_insertions": 340, "reference_words": 11943, "char_hits": 65614, "char_substitutions": 767, "char_deletions": 831, "char_insertions": 1739, "reference_chars": 67212, "exact_match_rate": 0.6461397058823529, "raw": { "wer": 0.13380758807588075, "cer": 0.06136771430225155, "mer": 0.13028778758142986, "wil": 0.21383086715891775, "wip": 0.7861691328410823, "word_hits": 10547, "word_substitutions": 1117, "word_deletions": 144, "word_insertions": 319, "reference_words": 11808, "char_hits": 66699, "char_substitutions": 1319, "char_deletions": 1090, "char_insertions": 1832, "reference_chars": 69108, "exact_match_rate": 0.4172794117647059 }, "orthographic": { "wer": 0.08015234870926788, "cer": 0.05039594692973985, "mer": 0.0780323005932762, "wil": 0.11757431144084218, "wip": 0.8824256885591578, "word_hits": 11189, "word_substitutions": 498, "word_deletions": 128, "word_insertions": 321, "reference_words": 11815, "char_hits": 65595, "char_substitutions": 811, "char_deletions": 901, "char_insertions": 1680, "reference_chars": 67307, "exact_match_rate": 0.6231617647058824 }, "wer_ci95": [ 0.06542025882580918, 0.09126204860193128 ], "cer_ci95": [ 0.041101972027671005, 0.06016230488018854 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.07736749560411957, "cer": 0.049648872225197885, "mer": 0.07522592200602458, "wil": 0.11118412348963358, "wip": 0.8888158765103664, "word_hits": 11359, "word_substitutions": 456, "word_deletions": 128, "word_insertions": 340, "reference_words": 11943, "char_hits": 65614, "char_substitutions": 767, "char_deletions": 831, "char_insertions": 1739, "reference_chars": 67212, "exact_match_rate": 0.6461397058823529 } }, "utterance_mean_wer": 0.08971144156575432, "utterance_mean_cer": 0.06200807096575261 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-bark-seedtts_en-000", "result_sha256": "27c98b9d4ddd0aea7c14be56f96969ced8ebc73a59fc2b0eae5282971e307910", "config_sha256": "0b105fc7c3e4aae28c9cb722d3da163b8bf1506a2a1ab99f83a1f1d5fde86b7e", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-bark-seedtts_en-001", "result_sha256": "ec9f141773a46e0eca377c07cf572c12431d6da046afc7158385f2edce045a6f", "config_sha256": "0e7078a2fbbdf3aadf0e832ca098579b00668aa7bb716f92840c2fc304abd366", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-bark-seedtts_en-002", "result_sha256": "c00728620e4e01e9e0f8d1ecfd66b132e47501224a15e810ef0ea116e513ec6c", "config_sha256": "4bbeac38a22b641809244a69474bdc2e8c5c747eb2de17e192a17caf2e19f798", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-bark-seedtts_en-003", "result_sha256": "d10750a3050ad69b9c3d5facc33163e36e14a8fca221b9cd5acf5fa4da799102", "config_sha256": "7f42c583268730fa45aa3b346bc4c0b05a58bd1915c95a749399a713073afc8a", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-bark-seedtts_en-004", "result_sha256": "2ec596ee13f2a918a5bbfa09c4579dc90a56f71b8183d188a1e15a49962eb543", "config_sha256": "3ac41208c26bb47e7043cd69b87f8baff50d8da6b45813b298995a8abc620906", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-bark-seedtts_en-005", "result_sha256": "951bcf2ad0a32897e0f40be97b9c7bd53395aad33db66e5db14525a0e48f68e5", "config_sha256": "050f7af5bd61b772bbb786dd1e192afdb27be90df23f1ffa342da45c9efa8f9c", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "conversationtts", "name": "ConversationTTS", "checkpoint": "artifacts/conversationtts/model.safetensors", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 11.374369565397501, "latency_p95_s": 21.11884947624052, "rtf": 2.6722347402449587, "peak_vram_mib": 4320.94140625, "audio_seconds": 5198.24, "clipping_ratio": 0.0010200252838765175, "silence_ratio": 0.22706196691592928, "rms_dbfs": -16.481099157390705, "normalization_id": "whisper_english", "wer": 0.08716402913840743, "cer": 0.0824703921918705, "mer": 0.08171756024805715, "wil": 0.0985030718625245, "wip": 0.9014969281374755, "word_hits": 11698, "word_substitutions": 216, "word_deletions": 29, "word_insertions": 796, "reference_words": 11943, "char_hits": 66731, "char_substitutions": 366, "char_deletions": 115, "char_insertions": 5062, "reference_chars": 67212, "exact_match_rate": 0.765625, "raw": { "wer": 0.12923441734417343, "cer": 0.09216009723910401, "mer": 0.1216033150051797, "wil": 0.17698255806140395, "wip": 0.823017441938596, "word_hits": 11023, "word_substitutions": 739, "word_deletions": 46, "word_insertions": 741, "reference_words": 11808, "char_hits": 67922, "char_substitutions": 844, "char_deletions": 342, "char_insertions": 5183, "reference_chars": 69108, "exact_match_rate": 0.5652573529411765 }, "orthographic": { "wer": 0.08954718578078713, "cer": 0.08382486219858261, "mer": 0.08401492892876995, "wil": 0.10351571145754379, "wip": 0.8964842885424562, "word_hits": 11535, "word_substitutions": 249, "word_deletions": 31, "word_insertions": 778, "reference_words": 11815, "char_hits": 66684, "char_substitutions": 394, "char_deletions": 229, "char_insertions": 5019, "reference_chars": 67307, "exact_match_rate": 0.7389705882352942 }, "wer_ci95": [ 0.06827334380474649, 0.10941677412955063 ], "cer_ci95": [ 0.05507506031858041, 0.11838151593873322 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.08716402913840743, "cer": 0.0824703921918705, "mer": 0.08171756024805715, "wil": 0.0985030718625245, "wip": 0.9014969281374755, "word_hits": 11698, "word_substitutions": 216, "word_deletions": 29, "word_insertions": 796, "reference_words": 11943, "char_hits": 66731, "char_substitutions": 366, "char_deletions": 115, "char_insertions": 5062, "reference_chars": 67212, "exact_match_rate": 0.765625 } }, "utterance_mean_wer": 0.09572835930129399, "utterance_mean_cer": 0.10447683402668193 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-conversationtts-seedtts_en-000", "result_sha256": "08d5a2ad6570723b33d69daca623a0ca558805073657883dfb5a4e8349e7f2d7", "config_sha256": "729bb9b0097d15399b29304042fcf6cc8168f5dda6aa18d14aaf9497dfb5d3f3", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-conversationtts-seedtts_en-001", "result_sha256": "351265482f8badafb25596e8a2777a065497b7bd6630293d0f354eb36c608839", "config_sha256": "43d3484a8d1da1d23c2a3a9012e767cc26eb98df20dd2a9f738fc3e105dd4c09", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-conversationtts-seedtts_en-002", "result_sha256": "b78fa14fc4910f66f28a33c826437fc6091149aa990bc79bd0798ba2e63dd68e", "config_sha256": "0eab4527d0226bc0402c2a3b414ce42a84be3c4d8c42105c3b4e3cd18ef7e75a", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-conversationtts-seedtts_en-003", "result_sha256": "d2b35d8abef7e2b952a3eb6626cc53b054f82baf08e3a797efceee36a3139c04", "config_sha256": "fe943826424e30ac65c97b5abe7a13c910ce1901d2ee2db1a7446f13d3839c8f", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-conversationtts-seedtts_en-004", "result_sha256": "d25018a753aa29d0d8ba102db54dd667246413a95db87e63efe29340d93999a0", "config_sha256": "67dd759cf81ada37c1b5925faa9e84aacc157633548c99b7ca8e34caec2ed657", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-conversationtts-seedtts_en-005", "result_sha256": "078caa6bbe9d3f9fe6e5989c20484f2d4a42f96fff4b564997e87f9763cabbed", "config_sha256": "caf91bac325a201464621212735a1cb6aec5507b3a9680c7a12d531c5235ea9b", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "vui", "name": "Vui", "checkpoint": "vui-abraham-100m.pt", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 1.9950699619948864, "latency_p95_s": 2.9318609584122894, "rtf": 0.4120764092569282, "peak_vram_mib": 3020.765625, "audio_seconds": 5821.52126984127, "clipping_ratio": 1.0284511102981117e-05, "silence_ratio": 0.36983417003042174, "rms_dbfs": -16.98248013674346, "normalization_id": "whisper_english", "wer": 0.12149376203633928, "cer": 0.08397310004165923, "mer": 0.11439608956165248, "wil": 0.15491850701861398, "wip": 0.845081492981386, "word_hits": 11233, "word_substitutions": 528, "word_deletions": 182, "word_insertions": 741, "reference_words": 11943, "char_hits": 65147, "char_substitutions": 1036, "char_deletions": 1029, "char_insertions": 3579, "reference_chars": 67212, "exact_match_rate": 0.4963235294117647, "raw": { "wer": 0.2035060975609756, "cer": 0.10363489031660589, "mer": 0.19237851252902088, "wil": 0.298564173075604, "wip": 0.701435826924396, "word_hits": 10088, "word_substitutions": 1516, "word_deletions": 204, "word_insertions": 683, "reference_words": 11808, "char_hits": 65826, "char_substitutions": 1888, "char_deletions": 1394, "char_insertions": 3880, "reference_chars": 69108, "exact_match_rate": 0.203125 }, "orthographic": { "wer": 0.13161235717308506, "cer": 0.08641003164603979, "mer": 0.12324641356899421, "wil": 0.16697574156173667, "wip": 0.8330242584382633, "word_hits": 11062, "word_substitutions": 569, "word_deletions": 184, "word_insertions": 802, "reference_words": 11815, "char_hits": 65091, "char_substitutions": 1068, "char_deletions": 1148, "char_insertions": 3600, "reference_chars": 67307, "exact_match_rate": 0.4742647058823529 }, "wer_ci95": [ 0.10961879047597937, 0.13331448614544683 ], "cer_ci95": [ 0.07456182716011253, 0.09409126504207617 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.12149376203633928, "cer": 0.08397310004165923, "mer": 0.11439608956165248, "wil": 0.15491850701861398, "wip": 0.845081492981386, "word_hits": 11233, "word_substitutions": 528, "word_deletions": 182, "word_insertions": 741, "reference_words": 11943, "char_hits": 65147, "char_substitutions": 1036, "char_deletions": 1029, "char_insertions": 3579, "reference_chars": 67212, "exact_match_rate": 0.4963235294117647 } }, "utterance_mean_wer": 0.1461771074776305, "utterance_mean_cer": 0.11014174174451084 }, "empty_asr_transcripts": 0, "quality_review": false, "inputs": [ { "run": "pub-v2-vui-seedtts_en-000", "result_sha256": "854a4d43db61268d19f20378eb39f40c519d1b79ba9879bc20c85533d85aa29a", "config_sha256": "258f1507962ab394a52eeca0ab249bdcc29611844427d826bfa28047aceefcc4", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-vui-seedtts_en-001", "result_sha256": "b52ea4e77779e2e9bfa46c4ff5d956c1ec761c12f07c7e8bee38b7825b9cbb1f", "config_sha256": "ac205f271d202b460d7aa90fea5b05c2b904f1f7d36f84185923f2cd1646c653", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-vui-seedtts_en-002", "result_sha256": "0fae9765f6d266c6d602d648745db56d3bbb6305ca2052879cc4812daa1ff364", "config_sha256": "f122b5f645d1ed4913294de72dfd44b95d135ddd3a31f56dadf240092a31f95e", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-vui-seedtts_en-003", "result_sha256": "0fc4b08492240cb0991076ba30473d22ac410b06c44d3b32adc303f4209f9ad2", "config_sha256": "a73e18c94b9e00257be6c39eaa67c66da06e4e23cf9259a5cbee922966ac5afd", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-vui-seedtts_en-004", "result_sha256": "13702a405059a3fd49adfab3dd5983b124c302df3e714c8c5f401b33f38ee103", "config_sha256": "ead8c4bd92a38e51bbda650111d9b632b1dc7a4999ce94f073eac94402808cb7", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-vui-seedtts_en-005", "result_sha256": "5a22ad36345ff9583401e4e66b16219b9f023de31c4770ad9a39b3afccd7339d", "config_sha256": "10ebf85a98ec76d000f1a2a548652fa7ac978a0e54966d290880fc359bfc4de2", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ] }, { "model": "cosyvoice", "name": "CosyVoice 3 · 0.5B · 2512", "checkpoint": "artifacts/cosyvoice3", "revision": null, "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "generation_limit_rate": 0.0, "generation_limit_samples": 0, "generation_limit_checks": 1088, "latency_p50_s": 2.650021158158779, "latency_p95_s": 3.798226011358201, "rtf": 0.7114221107347759, "peak_vram_mib": 3431.37841796875, "audio_seconds": 4108.52, "clipping_ratio": 0.0, "silence_ratio": 0.13905092033502137, "rms_dbfs": -2.7491495811524946, "normalization_id": "whisper_english", "wer": 0.13815624215021352, "cer": 0.07709932750104148, "mer": 0.13532354629705567, "wil": 0.2294798518533584, "wip": 0.7705201481466416, "word_hits": 10543, "word_substitutions": 1286, "word_deletions": 114, "word_insertions": 250, "reference_words": 11943, "char_hits": 63228, "char_substitutions": 2852, "char_deletions": 1132, "char_insertions": 1198, "reference_chars": 67212, "exact_match_rate": 0.41911764705882354, "raw": { "wer": 0.1814871273712737, "cer": 0.08764542455287376, "mer": 0.17836038285476488, "wil": 0.30532614643543954, "wip": 0.6946738535645605, "word_hits": 9872, "word_substitutions": 1802, "word_deletions": 134, "word_insertions": 207, "reference_words": 11808, "char_hits": 64297, "char_substitutions": 3404, "char_deletions": 1407, "char_insertions": 1246, "reference_chars": 69108, "exact_match_rate": 0.28308823529411764 }, "orthographic": { "wer": 0.1394837071519255, "cer": 0.07817908984206695, "mer": 0.1369908561928512, "wil": 0.23427870112445737, "wip": 0.7657212988755426, "word_hits": 10382, "word_substitutions": 1317, "word_deletions": 116, "word_insertions": 215, "reference_words": 11815, "char_hits": 63168, "char_substitutions": 2876, "char_deletions": 1263, "char_insertions": 1123, "reference_chars": 67307, "exact_match_rate": 0.40349264705882354 }, "wer_ci95": [ 0.12685322593416545, 0.14966956384385438 ], "cer_ci95": [ 0.07094589764337703, 0.08377590503471116 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.13815624215021352, "cer": 0.07709932750104148, "mer": 0.13532354629705567, "wil": 0.2294798518533584, "wip": 0.7705201481466416, "word_hits": 10543, "word_substitutions": 1286, "word_deletions": 114, "word_insertions": 250, "reference_words": 11943, "char_hits": 63228, "char_substitutions": 2852, "char_deletions": 1132, "char_insertions": 1198, "reference_chars": 67212, "exact_match_rate": 0.41911764705882354 } }, "utterance_mean_wer": 0.14817157392686525, "utterance_mean_cer": 0.08461964252927998 }, "empty_asr_transcripts": 0, "quality_review": true, "inputs": [ { "run": "pub-v2-cosyvoice-seedtts_en-000", "result_sha256": "d54540d064d2863ebc12049922ab790683afed777fcdb56ebdb7c0ce069ea3fe", "config_sha256": "547aed2b9b031f775ceadc94e40ee1b4f28c69cb5b56073781b2a929a5600a51", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-cosyvoice-seedtts_en-001", "result_sha256": "f98f2c91b3f9bdd537325fcd1a87f32556afacb329deb20ff82ae5ee5cce4e30", "config_sha256": "74d820cf1631c156a21a3520e28423154bb1fa4abd4d932d161a4a3176ffc525", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-cosyvoice-seedtts_en-002", "result_sha256": "b617b2624420b1abdc8fb6fd9f26fa762c494234f09c7870ae3341c35360b124", "config_sha256": "124df6039c110f8375badcd4597a5bda761951857cda7eb140772655c174af48", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-cosyvoice-seedtts_en-003", "result_sha256": "280cd6bb643342f09f04e2ae0a2f64f7d6911eef0cd0ab82f306ab67bba8fd91", "config_sha256": "309d5b6ffb66ddef1fe2501729ab019fe07ecf9333ff0c59e94f34609fb034b4", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-cosyvoice-seedtts_en-004", "result_sha256": "387fed9d1fe3d83f2d5145ba2301fca2fe9b04791c0c1dd47160b8d98c0641ba", "config_sha256": "328c44cc0a571c8ddbd269fd529a881393a77d58e423c4c3f99710349dac38a4", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-cosyvoice-seedtts_en-005", "result_sha256": "3df8c72f24879b25444b998f77115a3f017ded19b328dc246f38d64d9401dce0", "config_sha256": "02cca9f6392e44f635d98689d767ab8d8aaef5469df7b8e5ff18617813104d90", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ], "quality_review_reason": "Confirmed HiFT implementation bug in archived audio: magnitude clamp order and final LeakyReLU slope differ from publisher. Historical score invalidated; full corrected rerun started. Eight-text diagnostic is not the full score.", "upstream_checkpoint": "FunAudioLLM/Fun-CosyVoice3-0.5B-2512", "upstream_revision": "29e01c4e8d000f4bcd70751be16fa94bf3d85a18", "score_status": "invalidated_by_implementation_bug" }, { "model": "dia", "name": "Dia", "checkpoint": "nari-labs/Dia-1.6B-0626", "revision": "ef2795fcc29c5abe6ffc91fd33808588b49bbc66", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "generation_limit_rate": 0.0, "generation_limit_samples": 0, "generation_limit_checks": 1088, "latency_p50_s": 35.84547644108534, "latency_p95_s": 95.22943165823817, "rtf": 3.1889203149742467, "peak_vram_mib": 9100.61865234375, "audio_seconds": 15192.758276643992, "clipping_ratio": 4.931407476340513e-08, "silence_ratio": 0.19584809755048657, "rms_dbfs": -22.07775442813294, "normalization_id": "whisper_english", "wer": 0.673532613246253, "cer": 0.5928256858894245, "mer": 0.5234934270467265, "wil": 0.6199658900150475, "wip": 0.3800341099849525, "word_hits": 7322, "word_substitutions": 1067, "word_deletions": 3554, "word_insertions": 3423, "reference_words": 11943, "char_hits": 45280, "char_substitutions": 2362, "char_deletions": 19570, "char_insertions": 17913, "reference_chars": 67212, "exact_match_rate": 0.4522058823529412, "raw": { "wer": 0.6946985094850948, "cer": 0.6004225270590959, "mer": 0.5451222753854332, "wil": 0.6576072204602018, "wip": 0.3423927795397982, "word_hits": 6845, "word_substitutions": 1504, "word_deletions": 3459, "word_insertions": 3240, "reference_words": 11808, "char_hits": 46033, "char_substitutions": 2899, "char_deletions": 20176, "char_insertions": 18419, "reference_chars": 69108, "exact_match_rate": 0.29871323529411764 }, "orthographic": { "wer": 0.6753279729157851, "cer": 0.5921226618330931, "mer": 0.5243133131817584, "wil": 0.6225272886071618, "wip": 0.3774727113928382, "word_hits": 7239, "word_substitutions": 1108, "word_deletions": 3468, "word_insertions": 3403, "reference_words": 11815, "char_hits": 45310, "char_substitutions": 2368, "char_deletions": 19629, "char_insertions": 17857, "reference_chars": 67307, "exact_match_rate": 0.44669117647058826 }, "wer_ci95": [ 0.5772596992606132, 0.7770414764299733 ], "cer_ci95": [ 0.5068358244822976, 0.6812881581151855 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.673532613246253, "cer": 0.5928256858894245, "mer": 0.5234934270467265, "wil": 0.6199658900150475, "wip": 0.3800341099849525, "word_hits": 7322, "word_substitutions": 1067, "word_deletions": 3554, "word_insertions": 3423, "reference_words": 11943, "char_hits": 45280, "char_substitutions": 2362, "char_deletions": 19570, "char_insertions": 17913, "reference_chars": 67212, "exact_match_rate": 0.4522058823529412 } }, "utterance_mean_wer": 0.7629098579777105, "utterance_mean_cer": 0.6984215456512638 }, "empty_asr_transcripts": 183, "quality_review": true, "inputs": [ { "run": "pub-v2-dia-seedtts_en-000", "result_sha256": "8bf7583d118997cd752897e3ae052e8e7db93d47437a4436620525131a97d643", "config_sha256": "f28d85ee88dc19a0a584c4bada808ca7e2faea399fcf0ee6452e2414f5a9410d", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-dia-seedtts_en-001", "result_sha256": "ab045f4c0cdd5bd1317a7549d82e608749faaf63ec8b2a803c208ce714da2c18", "config_sha256": "e8088013a91de8c1f8a6df441423f772ab1d8db9dfbc1325c41f266cbc5c5a26", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-dia-seedtts_en-002", "result_sha256": "e3d404301bb3296f0a0eca252583bdc9c0fe4a4d2b6a88d4ca145dc0099d52ea", "config_sha256": "9afa0db4890a092383a2af66c12c2182c754d5bc40650b391bfa792fa69f6a87", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-dia-seedtts_en-003", "result_sha256": "298f73759dcd02e936682e13b4f212f38ec15ed97a6b7541d183f2758c2bc29e", "config_sha256": "256a17cf7ef58ac0eb4d093caf84e5a1def188ae5c011fc8ab772a314a7da355", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-dia-seedtts_en-004", "result_sha256": "df8c04aa68339213bbeb39da0897bfddb1607dae0451e3429743a83c1266f6be", "config_sha256": "d41deb303579852a547ca95561b2a32c0fc5dd905dc7e35f7a890315408e6966", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-dia-seedtts_en-005", "result_sha256": "f07179d6d4d2511308fd697f555ac26e3531498f7c0a044c97e56ae6e954e4b5", "config_sha256": "a2f1cd92b3e71111e8337f2386e5616051438d5121c6951f13f159bb99c2fc1c", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ], "quality_review_reason": "High WER remains under review. Three native/Transformers generation comparisons and independent DAC decoding did not establish a port defect. Empty transcripts and ASR repetition affect scores; diagnostic VAD does not restore missing speech." }, { "model": "llasa", "name": "Llasa", "checkpoint": "HKUSTAudio/Llasa-1B-Multilingual", "revision": "7f094cb62b0a9779b334c60d039a61c5a6e04456", "summary": { "attempted": 1088, "generated": 1088, "scored": 1088, "generation_failure_rate": 0.0, "latency_p50_s": 5.18002450093627, "latency_p95_s": 8.86913811042904, "rtf": 0.8671031698147694, "peak_vram_mib": 5498.3251953125, "audio_seconds": 7046.34, "clipping_ratio": 5.305286515617844e-06, "silence_ratio": 0.4975273408855499, "rms_dbfs": -29.792159225615766, "normalization_id": "whisper_english", "wer": 0.7399313405342042, "cer": 0.514342676902934, "mer": 0.6458851045168835, "wil": 0.835797418691164, "wip": 0.16420258130883603, "word_hits": 4845, "word_substitutions": 5386, "word_deletions": 1712, "word_insertions": 1739, "reference_words": 11943, "char_hits": 39011, "char_substitutions": 14900, "char_deletions": 13301, "char_insertions": 6369, "reference_chars": 67212, "exact_match_rate": 0.03125, "raw": { "wer": 0.7639735772357723, "cer": 0.5298952364415118, "mer": 0.6820656283078784, "wil": 0.8693770527911577, "wip": 0.1306229472088423, "word_hits": 4205, "word_substitutions": 5841, "word_deletions": 1762, "word_insertions": 1418, "reference_words": 11808, "char_hits": 39163, "char_substitutions": 16339, "char_deletions": 13606, "char_insertions": 6675, "reference_chars": 69108, "exact_match_rate": 0.014705882352941176 }, "orthographic": { "wer": 0.7349978840457047, "cer": 0.5129035612937733, "mer": 0.6479146459747818, "wil": 0.8385330123129942, "wip": 0.16146698768700582, "word_hits": 4719, "word_substitutions": 5366, "word_deletions": 1730, "word_insertions": 1588, "reference_words": 11815, "char_hits": 38963, "char_substitutions": 14821, "char_deletions": 13523, "char_insertions": 6178, "reference_chars": 67307, "exact_match_rate": 0.029411764705882353 }, "wer_ci95": [ 0.7104861781862367, 0.7706671980254735 ], "cer_ci95": [ 0.4929818523525938, 0.5394510820264022 ], "unique_prompts_scored": 1088, "by_category": { "read_speech": { "wer": 0.7399313405342042, "cer": 0.514342676902934, "mer": 0.6458851045168835, "wil": 0.835797418691164, "wip": 0.16420258130883603, "word_hits": 4845, "word_substitutions": 5386, "word_deletions": 1712, "word_insertions": 1739, "reference_words": 11943, "char_hits": 39011, "char_substitutions": 14900, "char_deletions": 13301, "char_insertions": 6369, "reference_chars": 67212, "exact_match_rate": 0.03125 } }, "utterance_mean_wer": 0.7637409496456972, "utterance_mean_cer": 0.5358505998889113 }, "empty_asr_transcripts": 16, "quality_review": true, "inputs": [ { "run": "pub-v2-llasa-seedtts_en-000", "result_sha256": "4d1d0b52978b28beb1fbf131df4b97481f798c069b6e04df86ade61d31710404", "config_sha256": "fe8a66b4cce91cf35225fb2f1053168ae0fafe6ef4706fd332396664e939a84c", "dataset_part_sha256": "d38a0f416c46b2c80ccee103e1675fbde938772ed749294bbfbdf81e03469e7c" }, { "run": "pub-v2-llasa-seedtts_en-001", "result_sha256": "616902188e2bd5328ee3fad54f8113476c70929d7f797a3e4ee7f34515bcd89a", "config_sha256": "0622eccc7ab6d8a324cdd9571b3e75e9b34344b9d8e1200a5c18cda8adc92c1f", "dataset_part_sha256": "42b276c4ae726fe57e1732d4d5181c726390e06cd683abd8f62cb970576f0943" }, { "run": "pub-v2-llasa-seedtts_en-002", "result_sha256": "3326c8107a18a7be7c8c89df38e4a6c1ea7be8d637466422cc29a3529883a155", "config_sha256": "28d2dcc9b719ab85efe7aece4a1aae816ecaa05074a3418f3a5306eb3b79e17d", "dataset_part_sha256": "70ba2ebdff1cb9b06b97d73ece1e6290f5e5b05790711c546e6bc13d061a10c1" }, { "run": "pub-v2-llasa-seedtts_en-003", "result_sha256": "6b15f1a373bf854b3658c9c445f32d999702cab899d6895992953a9c07f7aa24", "config_sha256": "f2ae95fa5a6e6b4e59ba17fe5ad434fb0f5aa948fa0ae0950f56c62507eda333", "dataset_part_sha256": "ea2356694a10f7c21cf7fbe9ef7dd2cc35c2bac9296f4e43edb2f8d63a866dca" }, { "run": "pub-v2-llasa-seedtts_en-004", "result_sha256": "8287b855eb87c5f2f90a7c4874669a6869f2841b6d34dc2a5f025779d2c66e00", "config_sha256": "2e8c43c82aaa0435862a0b277b5247324e4ef0b38a1c1d4e4df0d54fc189621d", "dataset_part_sha256": "cd1978d62a06a0fcc5f6599fe90af6b238580b8d398ae539bb59e09667019c85" }, { "run": "pub-v2-llasa-seedtts_en-005", "result_sha256": "e30eb431e5353e105060a878bf1b5f295c46643628f8ff542a2f6d5b1b6ada43", "config_sha256": "2a5fa06713b697123ec609a6fea6ed2bcf8f940a636a1967d66332e2c848b6b9", "dataset_part_sha256": "7dbeb30a8710c5ad4958677f4206868ce042ff7f796ac5b178da561e6c25a7a0" } ], "quality_review_reason": "High WER remains under review. Official top_k=50 differs from native default; setting it alone did not resolve errors. FP32 LM and legacy publisher XCodec2 comparisons agree closely on the audited examples." } ], "quality_audit": { "date": "2026-09-15", "report": "quality-audit.html", "original_scores_preserved": true, "cosyvoice_corrected_full_run": "in_progress", "corrected_full_score_available": false } }