Supported Languages
Features such as entity extraction and OCR depend on the language of the files you upload to Aleph. This reference lists the languages that are currently supported by Aleph:
If you need support for additional languages or have feedback about the quality of NER/OCR in certain languages, please let us know on GitHub.
| Language | Detection | OCR | NER |
|---|---|---|---|
| Afrikaans | ✅ | ✅ | |
| Albanian | ✅ | ✅ | |
| Arabic | ✅ | ||
| Armenian | ✅ | ✅ | |
| Azerbaijani | ✅ | ✅ | |
| Belarusian | ✅ | ✅ | |
| Bengali | ✅ | ||
| Bosnian | ✅ | ||
| Bulgarian | ✅ | ✅ | |
| Burmese | ✅ | ✅ | |
| Catalan | ✅ | ✅ | |
| Central Khmer | ✅ | ✅ | |
| Croatian | ✅ | ✅ | |
| Czech | ✅ | ✅ | |
| Danish | ✅ | ✅ | ✅ |
| Dutch | ✅ | ✅ | ✅ |
| English | ✅ | ✅ | ✅ |
| Estonian | ✅ | ✅ | |
| Filipino | ✅ | ||
| Finnish | ✅ | ✅ | |
| French | ✅ | ✅ | ✅ |
| Georgian | ✅ | ✅ | |
| German | ✅ | ✅ | ✅ |
| Greek | ✅ | ✅ | ✅ |
| Haitian | ✅ | ||
| Hebrew | ✅ | ✅ | |
| Hindi | ✅ | ✅ | |
| Hungarian | ✅ | ✅ | |
| Icelandic | ✅ | ✅ | |
| Indonesian | ✅ | ✅ | |
| Italian | ✅ | ✅ | ✅ |
| Japanese | ✅ | ||
| Kannada | ✅ | ✅ | |
| Kazakh | ✅ | ||
| Korean | ✅ | ||
| Kyrgyz | ✅ | ||
| Kurdish | ✅ | ||
| Latvian | ✅ | ✅ | |
| Lithuanian | ✅ | ✅ | ✅ |
| Macedonian | ✅ | ✅ | ✅ |
| Malay | ✅ | ✅ | |
| Maltese | ✅ | ✅ | |
| Mongolian | ✅ | ||
| Nepali | ✅ | ✅ | |
| Norwegian | ✅ | ✅ | ✅ |
| Persian | ✅ | ||
| Polish | ✅ | ✅ | ✅ |
| Portugese | ✅ | ✅ | ✅ |
| Romanian | ✅ | ✅ | ✅ |
| Russian | ✅ | ✅ | ✅ |
| Serbian | ✅ | ✅ | |
| Sinhala | ✅ | ||
| Slovak | ✅ | ✅ | |
| Slovenian | ✅ | ✅ | |
| Somali | ✅ | ||
| Spanish | ✅ | ✅ | ✅ |
| Swahili | ✅ | ✅ | |
| Swedish | ✅ | ✅ | |
| Tajik | ✅ | ||
| Tamil | ✅ | ||
| Thai | ✅ | ||
| Tibetan | ✅ | ||
| Turkish | ✅ | ✅ | |
| Turkmen | ✅ | ||
| Ukrainian | ✅ | ✅ | |
| Urdu | ✅ | ||
| Uzbek | ✅ | ✅ |