Croatian translation and speech-to-text models hr

5 models into Croatian, 4 from Croatian, 12 speech-to-text. Best scored into Croatian: German to Croatian (chrF++ 47.2). Best scored from Croatian: Croatian to French (chrF++ 55.6).

Which open models work for Croatian?

Windy Translate lists 5 open translation models into Croatian and 4 from Croatian. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 9 Apache-2.0 (terms and attribution text: licensing). 9 of them have a screening score on FLORES-200. The best scored into Croatian is translate-de-hr (chrF++ 47.2, Good). The best scored from Croatian is translate-hr-fr (chrF++ 55.6, Good).

With English. English to Croatian: no direct model here. Croatian to English: no direct model here.

By band, the scored Croatian models are 7 Good and 2 Usable (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. Whisper's tokenizer lists Croatian 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 Croatian

From Croatian

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