0.1.3

underpig1/octos0.1.3Apr 7, 2026by zhu-han

AI Summary

This release improves user experience by relaxing dependency constraints, adding new demo options for ASR and instruction following, and resolving text processing and audio backend issues.

Key Highlights

Relaxed PyTorch version requirements for better compatibility
Added 'no_asr' and 'instruct' options to the demo
Fixed text processing for non-verbal sounds and special symbols
Fixed torchaudio backend issues

New Features

'no_asr' and 'instruct' demo options
Relaxed PyTorch version constraints

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