Starstruk Logo MarkStarstruk

v1.12.0

k2-fsa/sherpa-onnxv1.12.0May 15, 2025by github-actions[bot]

AI Summary

This major feature release adds real-time speech recognition capabilities for SenseVoice, new C++ and Android examples, and WebSocket updates.

Key Highlights

  • Add real-time speech recognition example for SenseVoice
  • Add C++ example for streaming ASR with SenseVoice
  • Add Android demo for real-time ASR with non-streaming ASR models
  • Support sending is_eof for online websocket server
  • Add nodejs example for parakeet-tdt-0.6b-v2

New Features

  • SenseVoice real-time ASR example
  • Parakeet TDT Node.js example
  • Android real-time ASR demo
  • WebSocket EOF support

Full Release Notes

## What's Changed
* Fix building wheels for macOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2192
* Show verbose logs in homophone replacer by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2194
* Fix displaying streaming speech recognition results for Python. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2196
* Add real-time speech recognition example for SenseVoice. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2197
* docs: add Open-XiaoAI KWS project by @idootop in https://github.com/k2-fsa/sherpa-onnx/pull/2198
* Add C++ example for streaming ASR with SenseVoice. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2199
* Add C++ example for real-time ASR with nvidia/parakeet-tdt-0.6b-v2. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2201
* Add a link to YouTube video including sherpa-onnx. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2202
* Support sending is_eof for online websocket server. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2204
* Add alsa-based streaming ASR example for sense voice. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2207
* Support homophone replacer in Android asr demo. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2210
* Add a Go implementation of the TTS generation callback by @xiaokuang95 in https://github.com/k2-fsa/sherpa-onnx/pull/2213
* Add Android demo for real-time ASR with non-streaming ASR models. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2214
* Expose dither for JNI by @esavin in https://github.com/k2-fsa/sherpa-onnx/pull/2215
* Add nodejs example for parakeet-tdt-0.6b-v2. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2219
* Add script to build APK for simulated-streaming-asr. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2220
* Release v1.12.0 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/2221

## New Contributors
* @idootop made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/2198
* @esavin made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/2215

**Full Changelog**: https://github.com/k2-fsa/sherpa-onnx/compare/v1.11.5...v1.12.0