k2-fsa/sherpa-onnx
speech recognition, synthesis, and audio tools for many platforms
View on index · View in 3D Map
Related repos
- AI-powered audio processing tool with speech recognition, translation, and TTS
- open-weight text-to-speech model for fast, natural voice synthesis
- speech recognition toolkit for transcribing audio to text
- open-source model for speech-to-speech and audio understanding
- Text-to-speech system on devices via ONNX
- Trains speech recognition models in 24 hours for $12
- Offline voice recognition for Linux
- Text-to-speech engine for long-form audio
- audio foundation model for understanding, generation, and conversation
- open source speech recognition toolkit with ASR, VAD, speaker verification, and model zoo
