Sherpa-ONNX STT
Cross-platform speech recognition using ONNX Runtime for on-device ASR.
About
Sherpa-ONNX from the k2-fsa project, a modern successor to Kaldi, provides on-device speech recognition using ONNX Runtime, with both streaming and non-streaming models. It runs locally without internet on Android, iOS, Linux, macOS, Windows, embedded boards, and WebAssembly, and also supports text-to-speech and voice activity detection. Prebuilt models and demos are provided. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Convolution-augmented transformer for speech recognition in ESPnet toolkit.
End-to-end speech processing toolkit covering ASR, TTS, and speech translation.
CLI tool that transcribes audio 10x faster using pipeline optimizations.
Established speech recognition toolkit used in research and production systems.
Self-supervised speech representation model by Meta for ASR.
Multilingual ASR model by NVIDIA supporting 4 languages with translation.