Starstruk Logo MarkStarstruk

v1.10.15

k2-fsa/sherpa-onnxv1.10.15Jul 15, 2024by github-actions[bot]

AI Summary

Introduced int8 quantized Whisper large models, exported MeloTTS to ONNX, and added pre-trained models for the Libriheavy dataset. Includes a microphone example for .NET keyword spotting.

Key Highlights

  • Int8 quantized Whisper large models
  • Export MeloTTS to ONNX
  • Pre-trained models for Libriheavy dataset
  • Microphone example for .Net keyword spotting

New Features

  • Int8 quantized Whisper large models
  • Export MeloTTS to ONNX
  • Pre-trained models for Libriheavy dataset
  • Microphone example for .Net keyword spotting

Full Release Notes

## What's Changed
* Fix releasing dart packages by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1117
* Add microphone example for .Net keyword spotting by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1120
* Fix publishing apks to huggingface by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1121
* Add pre-trained models for the Libriheavy dataset by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1122
* Add int8 quantized whisper large models by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1126
* Allow modify model config at decode time for ASR by @iprovalo in https://github.com/k2-fsa/sherpa-onnx/pull/1124
* Export MeloTTS to ONNX by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1129
* Revert to onnxruntime 1.17.1 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/1131

## New Contributors
* @iprovalo made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/1124

**Full Changelog**: https://github.com/k2-fsa/sherpa-onnx/compare/v1.10.14...v1.10.15