Skip to content

feat: REST v1 (OpenAPI 3.1) + models index + ML inference proxy #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ronaldtse merged 1 commit into from
Aug 23, 2026
Merged

feat: REST v1 (OpenAPI 3.1) + models index + ML inference proxy #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,3 +80,19 @@ ruby -e '... see scripts/build-maps.rb ...'
`test/fixtures/parity.json` holds queries recorded from the production
Ruby API; CI replays them against this implementation. Zero-diff is the
release gate.


## REST v1 (OpenAPI)

REST endpoints serve alongside GraphQL (which remains at `POST /graphql`):

- `GET /openapi.json` — the OpenAPI 3.1 document
- `GET /v1/info` — version + capability summary
- `GET /v1/maps` / `GET /v1/maps/{code}` — bundled transliteration systems
- `POST /v1/transliterate` — `{system, input}` → `{output}`
- `POST /v1/detect` — `{input, output}` → ranked systems
- `GET /v1/models` / `GET /v1/models/{id}` — the neural model index (IMF v1, generated from interscript-ml's models.yaml via `npm run gen:models`)
- `POST /v1/infer` — `{model, input}` → `{output}`; proxies to the
inference service configured with `ML_ENDPOINT` + `ML_TOKEN` env vars
(Interscript runs `src/api/inference.py` on Modal: the same
parity-verified ONNX decode that gates every release)
312 changes: 312 additions & 0 deletions dist/src/generated/models.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,312 @@
{
"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": 0.0
},
"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": 0.0
},
"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": 0.0
},
"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": 29.0,
"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": 0.0
},
"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": 4.43,
"source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0"
},
{
"name": "per_student",
"value": 9.19,
"source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0"
}
],
"parity": {
"samples": 1219,
"cer_delta": 0.0
},
"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",
"value": 12.06,
"source": "interscript/interscript-ml docs/RESULTS.md#tha-g2p-small-1.0"
}
],
"parity": {
"samples": 1219,
"cer_delta": 0.0803
},
"license": "BSD-3-Clause"
},
{
"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",
"value": 12.06,
"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": 0.0
},
"license": "BSD-3-Clause"
},
{
"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": 0.0
},
"license": "BSD-3-Clause"
}
]
}
Loading
Loading