0.1.3

k2-fsa/OmniVoice0.1.3Apr 7, 2026by zhu-han

AI Summary

This release relaxes PyTorch version requirements and adds new demo options. It also includes fixes for text processing and torchaudio backend issues.

Key Highlights

Relaxed PyTorch version requirements
Added no_asr and instruct options to demo
Fixed text processing for non-verbal and special symbols
Fixed torchaudio backend

New Features

Added no_asr option to demo
Added instruct option to demo

Full Release Notes

## What's Changed
* Version 0.1.3 by @zhu-han in https://github.com/k2-fsa/OmniVoice/pull/61
  * relax pytorch version requirements 
  * Add tips in readme 
  * add no_asr and instruct options to demo 
  * fix text processing for non-verbal and special symbols 
  * fix torchaudio backend


**Full Changelog**: https://github.com/k2-fsa/OmniVoice/compare/0.1.2...0.1.3