F5-tts

**Full Changelog**: https://github.com/SWivid/F5-TTS/compare/1.0.3...1.0.8

- v1.0.8 fix a fatal bug with log_samples since 37eb3b50da8fdcb24f8b420b5f91246d85d4f5b5 that may be the root cause of training instability and unknown performance degradation
- v1.0.7 add no_zero_init v1 variant path to SHARED.md; add option in finetune gradio to save non-ema model weight
- v1.0.6 improves docker usage and along with other documentation
- v1.0.5 update finetune_gradio.py for clearer guidance
- v1.0.4 fix finetune_gradio.py vocab extend operation with checkpoint in .safetensors format

**Full Changelog**: https://github.com/SWivid/F5-TTS/compare/1.0.0...1.0.3

- v1.0.3 fix random seed and model loading in api.py 865
- v1.0.2 pass the `use_reentrant` in `torch.utils.checkpoint.checkpoint` explicitly for compatibility with torch>=2.4 859
- v1.0.1 memory management for extra large batches with chunk inference 851

**Full Changelog**: https://github.com/SWivid/F5-TTS/compare/0.6.2...1.0.0

**Major updates:**
- Add text padding mask for both filler tokens and padding tokens.
- Zero-initialize adaptive layernorm in DiT.
- Apply full Rotary Positional Embedding.

Thanks to everyone who has offered advice and support.

- F5-TTS v0 stable version for filing.
- Thanks again to everyone involved in this project.

**Full Changelog**: https://github.com/lucasnewman/f5-tts-mlx/compare/0.2.5...0.2.6

**Full Changelog**: https://github.com/lucasnewman/f5-tts-mlx/compare/0.2.4...0.2.5