facebookresearch/omnilingual-asr
Speech recognition for 1600 languages
View on index · View in 3D Map
Related repos
- AI models for translating and transcribing speech and text between many languages
- open source speech recognition toolkit with ASR, VAD, speaker verification, and model zoo
- open source text-to-speech engine for 100+ languages
- Speech processing package for developers
- Speech-to-text model for audio transcription, translation, and language detection
- AI multilingual speech recognition, translation, dubbing web app
- Speech-to-text apps in 99 languages
- Text-to-speech synthesis for over 7000 languages
- Run speech-to-text and translation with a Whisper-powered API that supports multiple engines and formats
- Transcribes speech into Windows applications locally
