Rohit Ghumare
3227f17628
English stays canonical. Translations generate to a separate translations
branch (never main); the site, README, and books all consume them. Default
engine is NLLB-200 in the CI runner: no API key, no Vercel cost.
One pipeline, three surfaces, none bloating main:
- lessons: 503 docs -> translations branch, fetched at runtime with English
fallback; English path byte-identical to before
- README: translated to the same branch, linked from the README header
- books: build_book.py --lang reads translated markdown and emits
aiefs-vol{n}-{slug}-<lang>.epub/.pdf release assets (English fallback)
- languages.json: 40-language registry (FLORES-200 + ci flag) driving the
script, the site switcher, and the CI matrix
- scripts/translate_lessons.py: prose-only walker keeps code/math/figures/
tables/HTML/bold/links/metadata out of the model (byte-lossless across all
503 lessons + README); per-language sha256 cache written per lesson so runs
resume and never redo unchanged English; providers pluggable (nllb default)
- .github/workflows/translate.yml + translate-requirements.txt: one job per
language, restores its cache, translates changed docs, pushes race-safe
- site switcher (40 languages, English fallback); build.js emits gitignored
site/langs.js from the registry
- docs/i18n.md: architecture, no-waste guarantee, cost, quality sample
252 lines
5.1 KiB
JSON
252 lines
5.1 KiB
JSON
{
|
|
"_comment": "Canonical language registry. English is the source. Adding a language here wires it into the translation script (scripts/translate_lessons.py) and the site switcher (via site/build.js -> site/langs.js). code = BCP-47-ish tag used in filenames and URLs; name = English name for the translation prompt; native = label shown in the switcher; ci = true means the auto push-triggered workflow builds this language (workflow_dispatch can still request any).",
|
|
"languages": [
|
|
{
|
|
"code": "en",
|
|
"name": "English",
|
|
"native": "English",
|
|
"source": true,
|
|
"nllb": "eng_Latn"
|
|
},
|
|
{
|
|
"code": "zh",
|
|
"name": "Simplified Chinese",
|
|
"native": "简体中文",
|
|
"nllb": "zho_Hans",
|
|
"ci": true
|
|
},
|
|
{
|
|
"code": "zh-TW",
|
|
"name": "Traditional Chinese",
|
|
"native": "繁體中文",
|
|
"nllb": "zho_Hant"
|
|
},
|
|
{
|
|
"code": "hi",
|
|
"name": "Hindi",
|
|
"native": "हिन्दी",
|
|
"nllb": "hin_Deva",
|
|
"ci": true
|
|
},
|
|
{
|
|
"code": "es",
|
|
"name": "Spanish",
|
|
"native": "Español",
|
|
"nllb": "spa_Latn",
|
|
"ci": true
|
|
},
|
|
{
|
|
"code": "ar",
|
|
"name": "Arabic",
|
|
"native": "العربية",
|
|
"nllb": "arb_Arab",
|
|
"ci": true
|
|
},
|
|
{
|
|
"code": "fr",
|
|
"name": "French",
|
|
"native": "Français",
|
|
"nllb": "fra_Latn"
|
|
},
|
|
{
|
|
"code": "pt",
|
|
"name": "Portuguese",
|
|
"native": "Português",
|
|
"nllb": "por_Latn"
|
|
},
|
|
{
|
|
"code": "bn",
|
|
"name": "Bengali",
|
|
"native": "বাংলা",
|
|
"nllb": "ben_Beng"
|
|
},
|
|
{
|
|
"code": "ru",
|
|
"name": "Russian",
|
|
"native": "Русский",
|
|
"nllb": "rus_Cyrl"
|
|
},
|
|
{
|
|
"code": "ja",
|
|
"name": "Japanese",
|
|
"native": "日本語",
|
|
"nllb": "jpn_Jpan"
|
|
},
|
|
{
|
|
"code": "de",
|
|
"name": "German",
|
|
"native": "Deutsch",
|
|
"nllb": "deu_Latn"
|
|
},
|
|
{
|
|
"code": "tr",
|
|
"name": "Turkish",
|
|
"native": "Türkçe",
|
|
"nllb": "tur_Latn",
|
|
"ci": true
|
|
},
|
|
{
|
|
"code": "ko",
|
|
"name": "Korean",
|
|
"native": "한국어",
|
|
"nllb": "kor_Hang"
|
|
},
|
|
{
|
|
"code": "it",
|
|
"name": "Italian",
|
|
"native": "Italiano",
|
|
"nllb": "ita_Latn"
|
|
},
|
|
{
|
|
"code": "vi",
|
|
"name": "Vietnamese",
|
|
"native": "Tiếng Việt",
|
|
"nllb": "vie_Latn"
|
|
},
|
|
{
|
|
"code": "id",
|
|
"name": "Indonesian",
|
|
"native": "Bahasa Indonesia",
|
|
"nllb": "ind_Latn"
|
|
},
|
|
{
|
|
"code": "th",
|
|
"name": "Thai",
|
|
"native": "ไทย",
|
|
"nllb": "tha_Thai"
|
|
},
|
|
{
|
|
"code": "pl",
|
|
"name": "Polish",
|
|
"native": "Polski",
|
|
"nllb": "pol_Latn"
|
|
},
|
|
{
|
|
"code": "uk",
|
|
"name": "Ukrainian",
|
|
"native": "Українська",
|
|
"nllb": "ukr_Cyrl"
|
|
},
|
|
{
|
|
"code": "nl",
|
|
"name": "Dutch",
|
|
"native": "Nederlands",
|
|
"nllb": "nld_Latn"
|
|
},
|
|
{
|
|
"code": "fa",
|
|
"name": "Persian",
|
|
"native": "فارسی",
|
|
"nllb": "pes_Arab"
|
|
},
|
|
{
|
|
"code": "ms",
|
|
"name": "Malay",
|
|
"native": "Bahasa Melayu",
|
|
"nllb": "zsm_Latn"
|
|
},
|
|
{
|
|
"code": "ta",
|
|
"name": "Tamil",
|
|
"native": "தமிழ்",
|
|
"nllb": "tam_Taml"
|
|
},
|
|
{
|
|
"code": "te",
|
|
"name": "Telugu",
|
|
"native": "తెలుగు",
|
|
"nllb": "tel_Telu"
|
|
},
|
|
{
|
|
"code": "mr",
|
|
"name": "Marathi",
|
|
"native": "मराठी",
|
|
"nllb": "mar_Deva"
|
|
},
|
|
{
|
|
"code": "ur",
|
|
"name": "Urdu",
|
|
"native": "اردو",
|
|
"nllb": "urd_Arab"
|
|
},
|
|
{
|
|
"code": "gu",
|
|
"name": "Gujarati",
|
|
"native": "ગુજરાતી",
|
|
"nllb": "guj_Gujr"
|
|
},
|
|
{
|
|
"code": "kn",
|
|
"name": "Kannada",
|
|
"native": "ಕನ್ನಡ",
|
|
"nllb": "kan_Knda"
|
|
},
|
|
{
|
|
"code": "he",
|
|
"name": "Hebrew",
|
|
"native": "עברית",
|
|
"nllb": "heb_Hebr"
|
|
},
|
|
{
|
|
"code": "el",
|
|
"name": "Greek",
|
|
"native": "Ελληνικά",
|
|
"nllb": "ell_Grek"
|
|
},
|
|
{
|
|
"code": "cs",
|
|
"name": "Czech",
|
|
"native": "Čeština",
|
|
"nllb": "ces_Latn"
|
|
},
|
|
{
|
|
"code": "ro",
|
|
"name": "Romanian",
|
|
"native": "Română",
|
|
"nllb": "ron_Latn"
|
|
},
|
|
{
|
|
"code": "hu",
|
|
"name": "Hungarian",
|
|
"native": "Magyar",
|
|
"nllb": "hun_Latn"
|
|
},
|
|
{
|
|
"code": "sv",
|
|
"name": "Swedish",
|
|
"native": "Svenska",
|
|
"nllb": "swe_Latn"
|
|
},
|
|
{
|
|
"code": "fi",
|
|
"name": "Finnish",
|
|
"native": "Suomi",
|
|
"nllb": "fin_Latn"
|
|
},
|
|
{
|
|
"code": "da",
|
|
"name": "Danish",
|
|
"native": "Dansk",
|
|
"nllb": "dan_Latn"
|
|
},
|
|
{
|
|
"code": "no",
|
|
"name": "Norwegian",
|
|
"native": "Norsk",
|
|
"nllb": "nob_Latn"
|
|
},
|
|
{
|
|
"code": "sw",
|
|
"name": "Swahili",
|
|
"native": "Kiswahili",
|
|
"nllb": "swh_Latn"
|
|
},
|
|
{
|
|
"code": "tl",
|
|
"name": "Filipino",
|
|
"native": "Filipino",
|
|
"nllb": "tgl_Latn"
|
|
}
|
|
]
|
|
}
|