Supported languages and recognition models

All text recognition models support Russian and English.

English-Russian model

This model works best, but supports only two languages:

  • en — English
  • ru — Russian

Important

Currently, this model can't be selected with automatic language detection. To use this model, you need to clearly specify one or both languages.

Latin-Cyrillic model

This model supports languages with the Latin and Cyrillic alphabets:

  • az — Azerbaijani
  • ba — Bashkir
  • be — Belarusian
  • bg — Bulgarian
  • bs — Bosnian
  • cs — Czech
  • da — Danish
  • de — German
  • en — English
  • es — Spanish
  • et — Estonian
  • fi — Finnish
  • fr — French
  • hu — Hungarian
  • id — Indonesian
  • it — Italian
  • kk — Kazakh
  • ky — Kirghiz
  • lt — Lithuanian
  • lv — Latvian
  • mt — Maltese
  • nl — Dutch
  • no — Norwegian
  • pl — Polish
  • pt — Portuguese
  • ro — Romanian
  • ru — Russian
  • sk — Slovak
  • sl — Slovenian
  • sv — Swedish
  • tg — Tajik
  • tr — Turkish
  • tt — Tatar
  • uz — Uzbek
  • vi — Vietnamese

Other models

Other models only support a single basic language plus Russian and English:

  • ar, en, ru — Arabic
  • el, en, ru — Greek
  • he, en, ru — Hebrew
  • hy, en, ru — Armenian
  • ja, en, ru — Japanese
  • ka, en, ru — Georgian
  • ko, en, ru — Korean
  • th, en, ru — Thai
  • zh, en, ru — Chinese

What's next