What's Changed
- Add audio.cpp to community projects by @0xShug0 in #209
- Make flex_attention honor autocast (fixes silent fp32 attention, ~4x training slowdown) by @shuaills in #212
- Honor asr_model_name when the ASR model is loaded lazily by @HenryVarro666 in #221
- Add VoiceClonePrompt.save()/load() for cross-session voice reuse by @HenryVarro666 in #223
- Fix ASR model always loading on GPU 0; add asr_device option by @HenryVarro666 in #224
- Avoid decoding the full reference audio just to get its duration by @aradix85 in #220
- Add opt-in text normalization (numbers, dates, currency) via generate(normalize_text=True) by @HenryVarro666 in #227
- Add stale issue workflow by @zhu-han in #228
New Contributors
- @0xShug0 made their first contribution in #209
- @shuaills made their first contribution in #212
- @HenryVarro666 made their first contribution in #221
- @aradix85 made their first contribution in #220
Full Changelog: 0.2.0...0.2.1