Korean translation and speech-to-text models ko

1 model into Korean, 10 from Korean, 12 speech-to-text. Best scored into Korean: English to Korean (chrF++ 2.8). Best scored from Korean: Korean to English (chrF++ 45.4).

Which open models work for Korean?

Windy Translate lists 1 open translation model into Korean and 10 from Korean. All of them can be downloaded from Hugging Face and run on your own hardware. By licence: 8 Apache-2.0 and 3 CC-BY-4.0 (terms and attribution text: licensing). 10 of them have a screening score on FLORES-200. The best scored into Korean is translate-tc-big-en-ko (chrF++ 2.8, Not recommended). The best scored from Korean is translate-ko-en (chrF++ 45.4, Good).

With English. English to Korean: translate-tc-big-en-ko (chrF++ 2.8, Not recommended). Korean to English: translate-ko-en (chrF++ 45.4, Good), the best of 3 direct models. To translate between Korean and a language with no direct model, you can go through English with these two.

By band, the scored Korean models are 1 Good, 7 Usable and 2 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. Whisper's tokenizer lists Korean 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 Korean

From Korean

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