{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihunreqqdn75iwgcbnee5puyofrdjimks23jersr5ln4kl45mwulu",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mjedhq37wpi2"
  },
  "path": "/t/best-models-for-english-japanese-and-english-chinese-translation/175201#post_1",
  "publishedAt": "2026-04-13T05:48:26.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Hi everyone\nI’m working on machine translation and need support for both:\n\n  * **English → Japanese**\n\n  * **English → Chinese**\n\n\n\n\nI wanted to understand **best practice here** :\n\n  * Is it better to use **separate language‑pair models** (e.g., en‑ja and en‑zh individually)?\n\n  * Or is there a **single multilingual model** that performs well for both (like NLLB or MADLAD) without a noticeable drop in quality?\n\n\n",
  "title": "Best models for English → Japanese and English → Chinese translation?"
}