OpenAI Whisper
OpenAI Whisper is one of the best open sourced speech models
- https://openai.com/index/whisper/
- GitHub - openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
Langauges
Whisper performs well in English but handles other languages:
- Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.
So can be used for translation as well as transcriptions.
Fast Whisper
Fast Whisper enables Whisper to be deployed with less resources.
Server
Whisper Server enables the whisper to be used by multiple applications easily.