| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-03-14 | 1.8 kB | |
| v0.4.1 source code.tar.gz | 2026-03-14 | 4.4 MB | |
| v0.4.1 source code.zip | 2026-03-14 | 4.6 MB | |
| Totals: 3 Items | 9.0 MB | 5 | |
What's Changed
- fix(lid): align ECAPA inference with SpeechBrain by @beshkenadze in https://github.com/Blaizzy/mlx-audio/pull/551
- add canary stt model (nvidia canary-1b-v2) by @mm65x in https://github.com/Blaizzy/mlx-audio/pull/550
- add moonshine stt model by @mm65x in https://github.com/Blaizzy/mlx-audio/pull/552
- add mms asr model by @mm65x in https://github.com/Blaizzy/mlx-audio/pull/553
- Add native MLX DeepFilterNet speech enhancement (v1/v2/v3) by @kylehowells in https://github.com/Blaizzy/mlx-audio/pull/561
- Update transformers to stable 5.x by @andimarafioti in https://github.com/Blaizzy/mlx-audio/pull/563
- Add Granite Speech 4.0 by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/565
- add fireredasr2-aed stt model by @mm65x in https://github.com/Blaizzy/mlx-audio/pull/559
- add sensevoice stt model by @mm65x in https://github.com/Blaizzy/mlx-audio/pull/556
- feat(audio_io): add OGG, Opus, and Vorbis audio format support for write operations by @irachex in https://github.com/Blaizzy/mlx-audio/pull/568
- Add support for Fish Audio S2 Pro TTS model by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/564
- Fish Audio S2 Pro: Fix high temp semantic token replacement for repeated tokens by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/573
- Update version.py by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/574
New Contributors
- @mm65x made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/550
- @kylehowells made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/561
- @irachex made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/568
Full Changelog: https://github.com/Blaizzy/mlx-audio/compare/v0.4.0...v0.4.1