What's Changed
- Use the high quality resampler for miniaudio-loaded audio files by @lucasnewman in #872
- Ignore unknown decode options in Whisper generate by @Lazarus-931 in #873
- fix(kokoro, kitten_tts): match PyTorch reference semantics in five decoder paths (-2.5 dB level error, F0-path misalignment, window mismatch) by @mchen04 in #859
- Add Nemotron VoiceChat codec by @lucasnewman in #876
- Fix unintentional float32 upcast for Qwen3-TTS by @lucasnewman in #879
- Improved Nemotron ASR streaming by @lucasnewman in #878
- Fix model type resolution for Higgs Audio v3 by @lucasnewman in #868
- Bump version to 0.4.8 by @Blaizzy in #883
New Contributors
Full Changelog: v0.4.7...v0.4.8
Contributors
Blaizzy, lucasnewman, and 2 other contributors