f5-tts-mlx 0.1.0

F5-TTS - MLX

F5 TTS — MLX

Implementation of F5-TTS, with the MLX framework.

F5 TTS is a non-autoregressive, zero-shot text-to-speech system using a flow-matching mel spectrogram generator with a diffusion transformer (DiT).

You can listen to a sample here that was generated in ~11 seconds on an M3 Max MacBook Pro.

F5 is an evolution of E2 TTS and improves performance with ConvNeXT v2 blocks for the learned text alignment. This repository is based on the original Pytorch implementation available here.

Installation

pip install f5-tts-mlx

Usage

python -m f5_tts_mlx.generate \
--text "The quick brown fox jumped over the lazy dog."

See examples/generate.py for more options.

—

You can load a pretrained model from Python like this:

from f5_tts_mlx import F5TTS

f5tts = F5TTS.from_pretrained("lucasnewman/f5-tts-mlx")

audio = f5tts.sample(...)

Pretrained model weights are also available on Hugging Face.

Appreciation

Yushen Chen for the original Pytorch implementation of F5 TTS and pretrained model.

Phil Wang for the E2 TTS implementation that this model is based on.

Citations

@article{chen-etal-2024-f5tts,
      title={F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching}, 
      author={Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen},
      journal={arXiv preprint arXiv:2410.06885},
      year={2024},
}

@inproceedings{Eskimez2024E2TE,
    title   = {E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS},
    author  = {Sefik Emre Eskimez and Xiaofei Wang and Manthan Thakker and Canrun Li and Chung-Hsien Tsai and Zhen Xiao and Hemin Yang and Zirun Zhu and Min Tang and Xu Tan and Yanqing Liu and Sheng Zhao and Naoyuki Kanda},
    year    = {2024},
    url     = {https://api.semanticscholar.org/CorpusID:270738197}
}

License

The code in this repository is released under the MIT license as found in the LICENSE file.