Metadata-Version: 2.1
Name: e2tts-mlx
Version: 0.0.1
Summary: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS in MLX
Home-page: https://github.com/JosefAlbers/e2tts-mlx
Author: Josef Albers
Author-email: albersj66@gmail.com
License: Apache License 2.0
Requires-Python: >=3.12.3
Description-Content-Type: text/markdown
Requires-Dist: vocos-mlx==0.0.5
Requires-Dist: soundfile==0.12.1
Requires-Dist: einops==0.8.0
Requires-Dist: einx==0.3.0
Requires-Dist: datasets==3.0.0
Requires-Dist: mlx==0.17.3
Requires-Dist: matplotlib==3.9.2
Requires-Dist: numpy==2.0.2
Requires-Dist: fire==0.6.0
Requires-Dist: huggingface-hub==0.24.7

# e2tts-mlx: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS in MLX

A lightweight implementation of [Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://arxiv.org/abs/2406.18009) model using MLX, with minimal dependencies and efficient computation on Apple Silicon.

## Quick Start

### Install

```zsh
# Quick install (note: PyPI version may not always be up to date)
pip install e2tts-mlx

# For the latest version, you can install directly from the repository:
# git clone https://github.com/JosefAlbers/e2tts-mlx.git
# cd e2tts-mlx
# pip install -e .
```

## Usage

To use a pre-trained model for text-to-speech:

```zsh
e2tts 'We must achieve our own salvation.'
```

https://github.com/user-attachments/assets/c022d622-2437-4dbf-b3ac-d0ce89322402

To train a new model:

```zsh
e2tts
```

![e2tts](https://raw.githubusercontent.com/JosefAlbers/e2tts-mlx/main/assets/e2tts.png)

## Acknowledgements

Thanks to [lucidrains](https://github.com/lucidrains/e2-tts-pytorch)' fantastic code that inspired this project.

## License

Apache License 2.0
