Armenian translation and speech-to-text models hy

2 models into Armenian, 2 from Armenian, 13 speech-to-text. Best scored into Armenian: English to Armenian (chrF++ 29.4). Best scored from Armenian: Armenian to Russian (chrF++ 31.4).

Which open models work for Armenian?

Windy Translate lists 2 open translation models into Armenian and 2 from Armenian. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 4 Apache-2.0 (terms and attribution text: licensing). 4 of them have a screening score on FLORES-200. The best scored into Armenian is translate-en-hy (chrF++ 29.4, Limited). The best scored from Armenian is translate-hy-ru (chrF++ 31.4, Usable).

With English. English to Armenian: translate-en-hy (chrF++ 29.4, Limited). Armenian to English: translate-hy-en (chrF++ 31.3, Usable). To translate between Armenian and a language with no direct model, you can go through English with these two.

By band, the scored Armenian models are 2 Usable and 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. 1 speech-to-text model made for Armenian: listen-windy-lingua-hy. Also, Whisper's tokenizer lists Armenian as one of its languages, so all 12 multilingual Whisper-based models here can transcribe it: see the speech models. Accuracy differs a lot between languages and model sizes, and this site has not measured speech accuracy.

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 Armenian

From Armenian

Armenian speech-to-text

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