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
Multilingual ASR model by NVIDIA supporting 4 languages with translation.
CLI tool that transcribes audio 10x faster using pipeline optimizations.
Self-supervised speech representation model by Meta for ASR.
High-performance C/C++ port of Whisper for CPU-based speech recognition.
Non-autoregressive ASR model by Alibaba achieving fast parallel transcription.
JAX-based Whisper implementation optimized for TPU/GPU with 70x+ speedup.