diff --git a/src/generated/models.json b/src/generated/models.json index ee87e89..a4dcf7a 100644 --- a/src/generated/models.json +++ b/src/generated/models.json @@ -1,449 +1,643 @@ { - "version": 1, - "models": [ - { - "id": "khm-latn-1.0", - "task": "translit", - "scripts": ["Khmr", "Latn"], - "precision": "fp32", - "filename": "khm-latn-1.0-fp32.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/khm-latn-1.0/khm-latn-1.0-fp32.zip", - "parts": null, - "sha256": "55993d473a2ed9489058779cad7e115db05e4020085b71616468cfae4f2f65cb", - "size": 1418009977, - "metrics": [ - { - "name": "cer", - "value": 27.42, - "source": "secryst/docs/RESULTS.md#khmer-transliteration-2026-08-14" - }, - { - "name": "em", - "value": 59.66, - "source": "secryst/docs/RESULTS.md#khmer-transliteration-2026-08-14" - } - ], - "parity": { - "samples": 895, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "urd-g2p-1.0", - "task": "g2p", - "scripts": ["Arab", "IPA"], - "precision": "fp32", - "filename": "urd-g2p-1.0-fp32.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/urd-g2p-1.0/urd-g2p-1.0-fp32.zip", - "parts": null, - "sha256": "9f0a248c7116aa7f6b9ac125fb9684a3556f3b8ce8b64567c05a5e7e7a018ebf", - "size": 1418039605, - "metrics": [ - { - "name": "cer", - "value": 14.77, - "source": "rababa-urdu/docs/RESULTS.md#g2p-urdu-text--ipa" - }, - { - "name": "em", - "value": 33.6, - "source": "rababa-urdu/docs/RESULTS.md#g2p-urdu-text--ipa" - } - ], - "parity": { - "samples": 12699, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "urd-diac-1.0", - "task": "diacritization", - "scripts": ["Arab", "Arab"], - "precision": "fp32", - "filename": "urd-diac-1.0-fp32.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/urd-diac-1.0/urd-diac-1.0-fp32.zip", - "parts": null, - "sha256": "c299ea44a4da4851a52283f8e42d2fb6f8c7a9c443ba7eb0270f97372e10b8ea", - "size": 1417851421, - "metrics": [ - { - "name": "cer", - "value": 3.74, - "source": "rababa-urdu/docs/RESULTS.md#diacritization-urdu-text--text--haraqat" - } - ], - "parity": { - "samples": 11940, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "heb-diac-1.0", - "task": "diacritization", - "scripts": ["Hebr", "Hebr"], - "precision": "fp32", - "filename": "heb-diac-1.0-fp32.zip", - "url": null, - "parts": [ - { - "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.0/heb-diac-1.0-fp32.zip.part-00", - "sha256": "5497f70cc3c96829e65f1eb0cc401c2d1ffeb4fa909acd4def824c2e019cbc37", - "size": 1500000000 - }, - { - "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.0/heb-diac-1.0-fp32.zip.part-01", - "sha256": "a7d2011ab4f9326a86e234cc49cb50daf82949e51efbf03a21d5796c46465e9d", - "size": 1281139753 - } - ], - "sha256": "b32fa239e0c56708b6004942de4b9e6e9f265e7cc3828f41d560e96386e20dd8", - "size": 2781139753, - "metrics": [ - { - "name": "der_greedy", - "value": 29, - "source": "rababa/docs/RESULTS.md#hebrew-diacritization" - }, - { - "name": "der_beam4", - "value": 17.46, - "source": "rababa/docs/RESULTS.md#hebrew-diacritization" - } - ], - "parity": { - "samples": 600, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "tha-g2p-base-1.0", - "task": "g2p", - "scripts": ["Thai", "IPA"], - "precision": "fp32", - "filename": "tha-g2p-base-1.0-fp32.zip", - "url": null, - "parts": [ - { - "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-00", - "sha256": "c4525414e5dec91a54d055ca9f1acd51c198f81fbfc55977aa82c1fb038d58d7", - "size": 1500000000 - }, - { - "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-01", - "sha256": "f5d11fbd75f92e8b5471add867418e2dd4f49a5e258b9ded2f3b5ffa630abe24", - "size": 1281174343 - } - ], - "sha256": "f341a5868867a9847d3f897d1fcc4d1d63b9a59b8913871bcf4ecab48f4fa895", - "size": 2781174343, - "metrics": [ - { - "name": "per_teacher", - "value": 1.25, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0" - }, - { - "name": "per_student", - "value": 3.53, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0" - } - ], - "parity": { - "samples": 1219, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "tha-g2p-small-1.0", - "task": "g2p", - "scripts": ["Thai", "IPA"], - "precision": "int8", - "filename": "tha-g2p-small-1.0-int8.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-small-1.0/tha-g2p-small-1.0-int8.zip", - "parts": null, - "sha256": "f2cfa93a42d98aabf08fdc82dfc6bd1574e21993f36558aa581fbe29e0588a94", - "size": 257468517, - "metrics": [ - { - "name": "per_teacher", - "value": 4.43, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - }, - { - "name": "per_student_beam4", - "value": 12.06, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - }, - { - "name": "per_student", - "value": 2.85, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - } - ], - "parity": { - "samples": 1219, - "cer_delta": 0.0803 - }, - "license": null - }, - { - "id": "tha-g2p-small-1.0-int4", - "task": "g2p", - "scripts": ["Thai", "IPA"], - "precision": "int4", - "filename": "tha-g2p-small-1.0-int4.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-small-1.0/tha-g2p-small-1.0-int4.zip", - "parts": null, - "sha256": "e5d12a3d65c6ac39fa08f52c975c99ff7a51c3e7b7aca7fbb461d2de2345e4cb", - "size": 201958073, - "metrics": [ - { - "name": "per_teacher", - "value": 4.43, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - }, - { - "name": "per_student_beam4", - "value": 12.06, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - }, - { - "name": "per_student", - "value": 2.85, - "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" - } - ], - "parity": { - "samples": 600, - "cer_delta": 0.0734 - }, - "license": "BSD-3-Clause" - }, - { - "id": "heb-diac-small-1.0", - "task": "diacritization", - "scripts": ["Hebr", "Hebr"], - "precision": "fp32", - "filename": "heb-diac-small-1.0-fp32.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-small-1.0/heb-diac-small-1.0-fp32.zip", - "parts": null, - "sha256": "905c53873d5a62bbe6252c6ec0ecef5f37e96e78cb01e8cd99b6b24c4d4d74ad", - "size": 1418663344, - "metrics": [ - { - "name": "der_teacher_greedy", - "value": 24.79, - "source": "interscript/interscript-ml docs/RESULTS.md#heb-diac-small-1.0" - }, - { - "name": "der_student_greedy", - "value": 30.37, - "source": "interscript/interscript-ml docs/RESULTS.md#heb-diac-small-1.0" - } - ], - "parity": { - "samples": 1864, - "cer_delta": 0 - }, - "license": null - }, - { - "id": "fas-g2p-1.0", - "task": "g2p", - "scripts": ["Arab", "Latn"], - "precision": "fp32", - "filename": "fas-g2p-1.0-fp32.zip", - "url": null, - "parts": [ - { - "url": "https://github.com/interscript/interscript-ml/releases/download/fas-g2p-1.0/fas-g2p-1.0-fp32.zip.part-00", - "sha256": "6c475e53f3c7ef3edcef5a24d2d81f51d13ddf4c417de98440943c9a32b03e55", - "size": 1500000000 - }, - { - "url": "https://github.com/interscript/interscript-ml/releases/download/fas-g2p-1.0/fas-g2p-1.0-fp32.zip.part-01", - "sha256": "c5656c649412f41e201c567e002514d31390b636d4650d9dcb6dfed1973fb3d5", - "size": 1280254270 - } - ], - "sha256": "b53fd69196127efcc596935d24e135b3c897006872c1646c674e70f3c0d9a0e3", - "size": 2780254270, - "metrics": [ - { - "name": "cer", - "value": 1.6, - "source": "interscript/interscript-ml docs/RESULTS.md#fas-g2p-1.0" - }, - { - "name": "sb_homograph_ezafe_norm", - "value": 77.34, - "source": "interscript/interscript-ml docs/RESULTS.md#fas-g2p-1.0" - } - ], - "parity": { - "samples": 1000, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "ara-diac-small-1.0", - "task": "diacritization", - "scripts": ["Arab", "Arab"], - "precision": "fp32", - "filename": "ara-diac-small-1.0-fp32.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-1.0/ara-diac-small-1.0-fp32.zip", - "parts": null, - "sha256": "8b149beb04294a2e482af876a34ae0fca3e87412606116fae1a376845fd4111a", - "size": 1418126835, - "metrics": [ - { - "name": "der_teacher_greedy", - "value": 1.3205, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_student_greedy", - "value": 3.658, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_teacher_fullset", - "value": 2.5815, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_student_fullset", - "value": 8.259, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - } - ], - "parity": { - "samples": 800, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "heb-diac-1.1", - "task": "diacritization", - "scripts": ["Hebr", "Hebr"], - "precision": "fp32", - "filename": "heb.zip", - "url": null, - "parts": [ - { - "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-00", - "sha256": "8dac0d62e9b0ac4b137412eaf3a542953f11575f12f66f76cb93d3f5d788fc1b", - "size": 1500000000 - }, - { - "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-01", - "sha256": "230c5ab731ea5f001f802d60b9e9a328c10b43bc311a19ef1974f114384313ed", - "size": 1280987905 - } - ], - "sha256": "f0022dde8d06e46e8f08cf0b2f7bbb887a05ed686b90f1d5aa82ca3ef690a0b0", - "size": 2780987905, - "metrics": [ - { - "name": "der_greedy", - "value": 16.44, - "source": "rababa/docs/RESULTS.md#hebrew-diacritization" - }, - { - "name": "der_beam4", - "value": 16.43, - "source": "rababa/docs/RESULTS.md#hebrew-diacritization" - } - ], - "parity": { - "samples": 500, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "ara-diac-1.0", - "task": "diacritization", - "scripts": ["Arab", "Arab"], - "precision": "fp32", - "filename": "ara-diac-1.0-fp32.zip", - "url": null, - "parts": [ - { - "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-1.0/ara-diac-1.0-fp32.zip.part-00", - "sha256": "6282a9291fb45ac7fcc3abe79d33b5913e91f87dcff8b305bf1d57ed98a3ed0b", - "size": 1500000000 - }, - { - "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-1.0/ara-diac-1.0-fp32.zip.part-01", - "sha256": "7e7254a89ec75493871f6f61a993315097dad1bb0ba63c4584453c309e8cb906", - "size": 1280311342 - } - ], - "sha256": "9e6d9777fe2474b150450774aaa1c9e8a9051b502b184fde298b91636dcfdac6", - "size": 2780311342, - "metrics": [ - { - "name": "der_total_greedy", - "value": 2.5793, - "source": "rababa/docs/RESULTS.md#r6-verdict-table-sadeeddiac-25-2026-08-21" - }, - { - "name": "der_morph_greedy", - "value": 1.5317, - "source": "rababa/docs/RESULTS.md#r6-verdict-table-sadeeddiac-25-2026-08-21" - } - ], - "parity": { - "samples": 500, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" - }, - { - "id": "ara-diac-small-1.0-int8", - "task": "diacritization", - "scripts": ["Arab", "Arab"], - "precision": "int8", - "filename": "ara-diac-small-1.0-int8.zip", - "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-1.0/ara-diac-small-1.0-int8.zip", - "parts": null, - "sha256": "af247d837bee7e755b5287102cfb715c48dc90c2cf41ec1c41e7238e1a72b678", - "size": 256959713, - "metrics": [ - { - "name": "der_teacher_greedy", - "value": 1.3205, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_student_greedy", - "value": 3.658, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_teacher_fullset", - "value": 2.5815, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - }, - { - "name": "der_student_fullset", - "value": 8.259, - "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" - } - ], - "parity": { - "samples": 800, - "cer_delta": 0 - }, - "license": "BSD-3-Clause" + "version": 1, + "models": [ + { + "id": "khm-latn-1.0", + "task": "translit", + "scripts": [ + "Khmr", + "Latn" + ], + "precision": "fp32", + "filename": "khm-latn-1.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/khm-latn-1.0/khm-latn-1.0-fp32.zip", + "parts": null, + "sha256": "55993d473a2ed9489058779cad7e115db05e4020085b71616468cfae4f2f65cb", + "size": 1418009977, + "metrics": [ + { + "name": "cer", + "value": 27.42, + "source": "secryst/docs/RESULTS.md#khmer-transliteration-2026-08-14" + }, + { + "name": "em", + "value": 59.66, + "source": "secryst/docs/RESULTS.md#khmer-transliteration-2026-08-14" + } + ], + "parity": { + "samples": 895, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "urd-g2p-1.0", + "task": "g2p", + "scripts": [ + "Arab", + "IPA" + ], + "precision": "fp32", + "filename": "urd-g2p-1.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/urd-g2p-1.0/urd-g2p-1.0-fp32.zip", + "parts": null, + "sha256": "9f0a248c7116aa7f6b9ac125fb9684a3556f3b8ce8b64567c05a5e7e7a018ebf", + "size": 1418039605, + "metrics": [ + { + "name": "cer", + "value": 14.77, + "source": "rababa-urdu/docs/RESULTS.md#g2p-urdu-text--ipa" + }, + { + "name": "em", + "value": 33.6, + "source": "rababa-urdu/docs/RESULTS.md#g2p-urdu-text--ipa" + } + ], + "parity": { + "samples": 12699, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "urd-diac-1.0", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "fp32", + "filename": "urd-diac-1.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/urd-diac-1.0/urd-diac-1.0-fp32.zip", + "parts": null, + "sha256": "c299ea44a4da4851a52283f8e42d2fb6f8c7a9c443ba7eb0270f97372e10b8ea", + "size": 1417851421, + "metrics": [ + { + "name": "cer", + "value": 3.74, + "source": "rababa-urdu/docs/RESULTS.md#diacritization-urdu-text--text--haraqat" + } + ], + "parity": { + "samples": 11940, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "heb-diac-1.0", + "task": "diacritization", + "scripts": [ + "Hebr", + "Hebr" + ], + "precision": "fp32", + "filename": "heb-diac-1.0-fp32.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.0/heb-diac-1.0-fp32.zip.part-00", + "sha256": "5497f70cc3c96829e65f1eb0cc401c2d1ffeb4fa909acd4def824c2e019cbc37", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.0/heb-diac-1.0-fp32.zip.part-01", + "sha256": "a7d2011ab4f9326a86e234cc49cb50daf82949e51efbf03a21d5796c46465e9d", + "size": 1281139753 + } + ], + "sha256": "b32fa239e0c56708b6004942de4b9e6e9f265e7cc3828f41d560e96386e20dd8", + "size": 2781139753, + "metrics": [ + { + "name": "der_greedy", + "value": 29, + "source": "rababa/docs/RESULTS.md#hebrew-diacritization" + }, + { + "name": "der_beam4", + "value": 17.46, + "source": "rababa/docs/RESULTS.md#hebrew-diacritization" + } + ], + "parity": { + "samples": 600, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "tha-g2p-base-1.0", + "task": "g2p", + "scripts": [ + "Thai", + "IPA" + ], + "precision": "fp32", + "filename": "tha-g2p-base-1.0-fp32.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-00", + "sha256": "c4525414e5dec91a54d055ca9f1acd51c198f81fbfc55977aa82c1fb038d58d7", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-01", + "sha256": "f5d11fbd75f92e8b5471add867418e2dd4f49a5e258b9ded2f3b5ffa630abe24", + "size": 1281174343 + } + ], + "sha256": "f341a5868867a9847d3f897d1fcc4d1d63b9a59b8913871bcf4ecab48f4fa895", + "size": 2781174343, + "metrics": [ + { + "name": "per_teacher", + "value": 1.25, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0" + }, + { + "name": "per_student", + "value": 3.53, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0" + } + ], + "parity": { + "samples": 1219, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "tha-g2p-small-1.0", + "task": "g2p", + "scripts": [ + "Thai", + "IPA" + ], + "precision": "int8", + "filename": "tha-g2p-small-1.0-int8.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-small-1.0/tha-g2p-small-1.0-int8.zip", + "parts": null, + "sha256": "f2cfa93a42d98aabf08fdc82dfc6bd1574e21993f36558aa581fbe29e0588a94", + "size": 257468517, + "metrics": [ + { + "name": "per_teacher", + "value": 4.43, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + }, + { + "name": "per_student_beam4", + "value": 12.06, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + }, + { + "name": "per_student", + "value": 2.85, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + } + ], + "parity": { + "samples": 1219, + "cer_delta": 0.0803 + }, + "license": null + }, + { + "id": "tha-g2p-small-1.0-int4", + "task": "g2p", + "scripts": [ + "Thai", + "IPA" + ], + "precision": "int4", + "filename": "tha-g2p-small-1.0-int4.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/tha-g2p-small-1.0/tha-g2p-small-1.0-int4.zip", + "parts": null, + "sha256": "e5d12a3d65c6ac39fa08f52c975c99ff7a51c3e7b7aca7fbb461d2de2345e4cb", + "size": 201958073, + "metrics": [ + { + "name": "per_teacher", + "value": 4.43, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + }, + { + "name": "per_student_beam4", + "value": 12.06, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + }, + { + "name": "per_student", + "value": 2.85, + "source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0" + } + ], + "parity": { + "samples": 600, + "cer_delta": 0.0734 + }, + "license": "BSD-3-Clause" + }, + { + "id": "heb-diac-small-1.0", + "task": "diacritization", + "scripts": [ + "Hebr", + "Hebr" + ], + "precision": "fp32", + "filename": "heb-diac-small-1.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-small-1.0/heb-diac-small-1.0-fp32.zip", + "parts": null, + "sha256": "905c53873d5a62bbe6252c6ec0ecef5f37e96e78cb01e8cd99b6b24c4d4d74ad", + "size": 1418663344, + "metrics": [ + { + "name": "der_teacher_greedy", + "value": 24.79, + "source": "interscript/interscript-ml docs/RESULTS.md#heb-diac-small-1.0" + }, + { + "name": "der_student_greedy", + "value": 30.37, + "source": "interscript/interscript-ml docs/RESULTS.md#heb-diac-small-1.0" + } + ], + "parity": { + "samples": 1864, + "cer_delta": 0 + }, + "license": null + }, + { + "id": "fas-g2p-1.0", + "task": "g2p", + "scripts": [ + "Arab", + "Latn" + ], + "precision": "fp32", + "filename": "fas-g2p-1.0-fp32.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/fas-g2p-1.0/fas-g2p-1.0-fp32.zip.part-00", + "sha256": "6c475e53f3c7ef3edcef5a24d2d81f51d13ddf4c417de98440943c9a32b03e55", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/fas-g2p-1.0/fas-g2p-1.0-fp32.zip.part-01", + "sha256": "c5656c649412f41e201c567e002514d31390b636d4650d9dcb6dfed1973fb3d5", + "size": 1280254270 + } + ], + "sha256": "b53fd69196127efcc596935d24e135b3c897006872c1646c674e70f3c0d9a0e3", + "size": 2780254270, + "metrics": [ + { + "name": "cer", + "value": 1.6, + "source": "interscript/interscript-ml docs/RESULTS.md#fas-g2p-1.0" + }, + { + "name": "sb_homograph_ezafe_norm", + "value": 77.34, + "source": "interscript/interscript-ml docs/RESULTS.md#fas-g2p-1.0" + } + ], + "parity": { + "samples": 1000, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-small-1.0", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "fp32", + "filename": "ara-diac-small-1.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-1.0/ara-diac-small-1.0-fp32.zip", + "parts": null, + "sha256": "8b149beb04294a2e482af876a34ae0fca3e87412606116fae1a376845fd4111a", + "size": 1418126835, + "metrics": [ + { + "name": "der_teacher_greedy", + "value": 1.3205, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_student_greedy", + "value": 3.658, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_teacher_fullset", + "value": 2.5815, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_student_fullset", + "value": 8.259, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + } + ], + "parity": { + "samples": 800, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "heb-diac-1.1", + "task": "diacritization", + "scripts": [ + "Hebr", + "Hebr" + ], + "precision": "fp32", + "filename": "heb.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-00", + "sha256": "8dac0d62e9b0ac4b137412eaf3a542953f11575f12f66f76cb93d3f5d788fc1b", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/heb-diac-1.1/heb.zip.part-01", + "sha256": "230c5ab731ea5f001f802d60b9e9a328c10b43bc311a19ef1974f114384313ed", + "size": 1280987905 + } + ], + "sha256": "f0022dde8d06e46e8f08cf0b2f7bbb887a05ed686b90f1d5aa82ca3ef690a0b0", + "size": 2780987905, + "metrics": [ + { + "name": "der_greedy", + "value": 16.44, + "source": "rababa/docs/RESULTS.md#hebrew-diacritization" + }, + { + "name": "der_beam4", + "value": 16.43, + "source": "rababa/docs/RESULTS.md#hebrew-diacritization" + } + ], + "parity": { + "samples": 500, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-1.0", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "fp32", + "filename": "ara-diac-1.0-fp32.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-1.0/ara-diac-1.0-fp32.zip.part-00", + "sha256": "6282a9291fb45ac7fcc3abe79d33b5913e91f87dcff8b305bf1d57ed98a3ed0b", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-1.0/ara-diac-1.0-fp32.zip.part-01", + "sha256": "7e7254a89ec75493871f6f61a993315097dad1bb0ba63c4584453c309e8cb906", + "size": 1280311342 + } + ], + "sha256": "9e6d9777fe2474b150450774aaa1c9e8a9051b502b184fde298b91636dcfdac6", + "size": 2780311342, + "metrics": [ + { + "name": "der_total_greedy", + "value": 2.5793, + "source": "rababa/docs/RESULTS.md#r6-verdict-table-sadeeddiac-25-2026-08-21" + }, + { + "name": "der_morph_greedy", + "value": 1.5317, + "source": "rababa/docs/RESULTS.md#r6-verdict-table-sadeeddiac-25-2026-08-21" + } + ], + "parity": { + "samples": 500, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-small-1.0-int8", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "int8", + "filename": "ara-diac-small-1.0-int8.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-1.0/ara-diac-small-1.0-int8.zip", + "parts": null, + "sha256": "af247d837bee7e755b5287102cfb715c48dc90c2cf41ec1c41e7238e1a72b678", + "size": 256959713, + "metrics": [ + { + "name": "der_teacher_greedy", + "value": 1.3205, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_student_greedy", + "value": 3.658, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_teacher_fullset", + "value": 2.5815, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + }, + { + "name": "der_student_fullset", + "value": 8.259, + "source": "interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0" + } + ], + "parity": { + "samples": 800, + "cer_delta": 0 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-small-2.0", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "fp32", + "filename": "ara-diac-small-2.0-fp32.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-2.0/ara-diac-small-2.0-fp32.zip", + "parts": null, + "sha256": "d9aa95d0e8fd0d7da80fd2f7dabedf0ac65f55ba984de565d252f5e14906d98c", + "size": 1418516306, + "metrics": [ + { + "name": "der_teacher_fullset", + "value": 2.289, + "source": "interscript/interscript-ml docs/RESULTS.md#run-006-r7-muon" + }, + { + "name": "der_student_fullset", + "value": 4.8218, + "source": "interscript/interscript-ml docs/RESULTS.md#run-006-r7-muon" + } + ], + "parity": { + "samples": 600, + "cer_delta": 0.1187 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-small-2.0-int8", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "int8", + "filename": "ara-diac-small-2.0-int8.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-2.0/ara-diac-small-2.0-int8.zip", + "parts": null, + "sha256": "f4d07acdaf9c18cded97e15e0c5636e6cee90de2fa32c5a373a44c0cc912bf50", + "size": 264043016, + "metrics": [ + { + "name": "der_teacher_fullset", + "value": 2.289, + "source": "interscript/interscript-ml docs/RESULTS.md#run-006-r7-muon" + }, + { + "name": "der_student_fullset", + "value": 4.8218, + "source": "interscript/interscript-ml docs/RESULTS.md#run-006-r7-muon" + } + ], + "parity": { + "samples": 600, + "cer_delta": 0.1393 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-2.0", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "fp32", + "filename": "ara-diac-2.0-fp32.zip", + "url": null, + "parts": [ + { + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-2.0/ara-diac-2.0-fp32.zip.part-00", + "sha256": "28c272b5ce58031c356e75823eb581f12351a1675a52d8e4000f851c80d5e14d", + "size": 1500000000 + }, + { + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-2.0/ara-diac-2.0-fp32.zip.part-01", + "sha256": "86016da35e14a8fc05d4fbf3b1ad9ef24c29f9f7893f1716e40bef4b491effa2", + "size": 1280299051 + } + ], + "sha256": "872c655ec6750bf44e5986f958de26767eafa13f8e0a7c64340bc35fd8a4550e", + "size": 2780299051, + "metrics": [ + { + "name": "der_total_greedy", + "value": 2.2864, + "source": "rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28" + }, + { + "name": "der_morph_greedy", + "value": 1.3343, + "source": "rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28" + }, + { + "name": "wer_wikinews_multiref", + "value": 17.3794, + "source": "rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28" + }, + { + "name": "der_wikinews_multiref", + "value": 11.8273, + "source": "rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28" + } + ], + "parity": { + "samples": 600, + "cer_delta": 0.0903 + }, + "license": "BSD-3-Clause" + }, + { + "id": "ara-diac-2.0-int8", + "task": "diacritization", + "scripts": [ + "Arab", + "Arab" + ], + "precision": "int8", + "filename": "ara-diac-2.0-int8.zip", + "url": "https://github.com/interscript/interscript-ml/releases/download/ara-diac-2.0/ara-diac-2.0-int8.zip", + "parts": null, + "sha256": "7f1d55d43f97564ad62fc14a7e0cabe52c01d8298b747677a75900de748bb6c6", + "size": 519207340, + "metrics": [ + { + "name": "der_total_greedy", + "value": 2.2864, + "source": "rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28" + }, + { + "name": "der_morph_greedy", + "value": 1.3343, + "source": "rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28" + }, + { + "name": "wer_wikinews_multiref", + "value": 17.3794, + "source": "rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28" + }, + { + "name": "der_wikinews_multiref", + "value": 11.8273, + "source": "rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28" } - ] + ], + "parity": { + "samples": 600, + "cer_delta": 0.0947 + }, + "license": "BSD-3-Clause" + } + ] }