Mossi translation models mos

4 models into Mossi, 1 from Mossi. Best scored into Mossi: English to Mossi (chrF++ 17.2). Best scored from Mossi: Mossi to English (chrF++ 18.6).

Which open models work for Mossi?

Windy Translate lists 4 open translation models into Mossi and 1 from Mossi. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 5 Apache-2.0 (terms and attribution text: licensing). 5 of them have a screening score on FLORES-200. The best scored into Mossi is translate-en-mos (chrF++ 17.2, Limited). The best scored from Mossi is translate-mos-en (chrF++ 18.6, Limited).

With English. English to Mossi: translate-en-mos (chrF++ 17.2, Limited). Mossi to English: translate-mos-en (chrF++ 18.6, Limited). To translate between Mossi and a language with no direct model, you can go through English with these two.

By band, the scored Mossi models are 4 Limited and 1 Not recommended (Excellent is chrF++ 60 or more, Good 45 to 60, Usable 30 to 45, Limited 15 to 30). A score is a 48-sentence screening of news and encyclopedia text, not a measure of accuracy, and a difference of a point or two is noise. How we measured.

Speech-to-text. No speech model here covers Mossi: there is no dedicated model, and Whisper's tokenizer does not list the language.

Each model page has a short snippet to download and run the model yourself, its licence and attribution text, and its score where there is one. Pick the best scored model for your direction, then try it on a few sentences of your own text: a screening score is a starting point, not a guarantee.

Into Mossi

From Mossi

Scores: chrF++ on FLORES-200 dev, 48 sentences, measured 2026-08-04. Method.