Tetela translation models tll
5 models into Tetela, 5 from Tetela.
Which open models work for Tetela?
Windy Translate lists 5 open translation models into Tetela and 5 from Tetela. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 10 Apache-2.0 (terms and attribution text: licensing). None of them has a screening score yet: FLORES-200, the test set used here, does not cover these pairs, so test them on your own text before you rely on them.
With English. English to Tetela: translate-en-tll (not yet scored). Tetela to English: translate-tll-en (not yet scored). To translate between Tetela and a language with no direct model, you can go through English with these two.
Speech-to-text. No speech model here covers Tetela: 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 Tetela
| Model | chrF++ (FLORES-200 dev) | Licence |
|---|---|---|
| English to Tetela language-verified translate-en-tll | not in FLORES-200 | Apache-2.0 |
| Spanish to Tetela translate-es-tll | not in FLORES-200 | Apache-2.0 |
| Finnish to Tetela translate-fi-tll | not in FLORES-200 | Apache-2.0 |
| French to Tetela translate-fr-tll | not in FLORES-200 | Apache-2.0 |
| Swedish to Tetela translate-sv-tll | not in FLORES-200 | Apache-2.0 |
From Tetela
| Model | chrF++ (FLORES-200 dev) | Licence |
|---|---|---|
| Tetela to English translate-tll-en | not in FLORES-200 | Apache-2.0 |
| Tetela to Spanish translate-tll-es | not in FLORES-200 | Apache-2.0 |
| Tetela to Finnish translate-tll-fi | not in FLORES-200 | Apache-2.0 |
| Tetela to French translate-tll-fr | not in FLORES-200 | Apache-2.0 |
| Tetela to Swedish translate-tll-sv | not in FLORES-200 | Apache-2.0 |
Scores: chrF++ on FLORES-200 dev, 48 sentences, measured 2026-08-04. Method.