Swati translation models ss

1 model into Swati, 1 from Swati. Best scored into Swati: English to Swati (chrF++ 22.0). Best scored from Swati: Swati to English (chrF++ 21.3).

Which open models work for Swati?

Windy Translate lists 1 open translation model into Swati and 1 from Swati. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 2 Apache-2.0 (terms and attribution text: licensing). 2 of them have a screening score on FLORES-200. The best scored into Swati is translate-en-ss (chrF++ 22.0, Limited). The best scored from Swati is translate-ss-en (chrF++ 21.3, Limited).

With English. English to Swati: translate-en-ss (chrF++ 22.0, Limited). Swati to English: translate-ss-en (chrF++ 21.3, Limited). To translate between Swati and a language with no direct model, you can go through English with these two.

By band, the scored Swati models are 2 Limited (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 Swati: 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 Swati

From Swati

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