Page MenuHomePhabricator

Enable MinT for all the remaining languages supported by NLLB-200
Closed, ResolvedPublic

Description

After several rounds of enablements of MinT for languages supported by NLLB-200 including those not supported by other services (T326578) and those with the mobile translation experience available (T339105), NLLB-200 is used to support 152 languages in Content and Section translation. However, NLLB-200 could support an additional set of Wikipedias.

This ticket proposes to enable MinT using NLLB-200 as an option for the following languages:

  1. Scottish Gaelic (gd/gla_Latn) — ✅
  2. Hungarian (hu/hun_Latn) — ✅
  3. Italian (it/ita_Latn) — ✅
  4. Kazakh (kk/kaz_Cyrl) — ✅
  5. Kyrgyz (ky/kir_Cyrl) — ✅
  6. Minangkabau (min/min_Latn) — ✅
  7. Dutch (nl/nld_Latn) — ✅
  8. Polish (pl/pol_Latn) — ✅
  9. Sardinian (sc/srd_Latn) — ✅
  10. Swedish (sv/swe_Latn) — ✅
  11. Ukrainian (uk/ukr_Cyrl) — ✅
  12. Vietnamese (vi/vie_Latn) — ✅
  13. Finnish (fi/fin_Latn) — ✅ Another ticket (T333969) will add support using OPusMT for specific pairs, but enabling NLLB-200 will be useful as a fallback model for all language pair combinations.
  14. Simple English (simple/eng_Latn) — ✅ Already enabled
  15. Japanese (ja/jpn_Jpan)
  16. German (de/deu_Latn)
  17. English (en/eng_Latn)

Ideally, all languages listed in NLLB-200 documentation should be available for Content Translation with MinT, with the exceptions of languages where MT has not been enabled yet (English and German), requested to be disabled (Japanese in T323973), and those languages with no Wikipedias yet (T336683).

Steps:

Event Timeline

Pginer-WMF updated the task description. (Show Details)
Pginer-WMF updated the task description. (Show Details)

Change 937490 had a related patch set uploaded (by KartikMistry; author: KartikMistry):

[mediawiki/services/cxserver@master] Enable MinT for all the remaining languages supported by NLLB-200

https://gerrit.wikimedia.org/r/937490

Change 937490 merged by jenkins-bot:

[mediawiki/services/cxserver@master] Enable MinT for all the remaining languages supported by NLLB-200

https://gerrit.wikimedia.org/r/937490

Change 937578 had a related patch set uploaded (by Santhosh; author: Santhosh):

[operations/deployment-charts@master] Update cxserver to 2023-07-13-063245-production

https://gerrit.wikimedia.org/r/937578

Change 937578 merged by jenkins-bot:

[operations/deployment-charts@master] Update cxserver to 2023-07-13-063245-production

https://gerrit.wikimedia.org/r/937578

Mentioned in SAL (#wikimedia-operations) [2023-08-01T05:26:54Z] <kart_> Updated cxserver to 2023-07-13-063245-production (T340953)

KartikMistry updated the task description. (Show Details)

@UOzurumba You can now go ahead with notifying communities about MinT enablement.

@UOzurumba You can now go ahead with notifying communities about MinT enablement.

Thanks! will do it this week.