Metadata-Version: 2.4
Name: ttstune
Version: 0.1.0
Summary: Configuration-driven framework for fine-tuning TTS models.
Author-email: mrfakename <me@mrfake.name>
License: MIT OR Apache-2.0
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE.APACHE
License-File: LICENSE.MIT
Requires-Dist: click
Provides-Extra: dev
Requires-Dist: ruff; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pre-commit; extra == "dev"
Dynamic: license-file

# TTSTune

Configuration-driven framework for fine-tuning TTS models.

## Roadmap

- Chatterbox
- F5-TTS
- CSM 1B
- Orpheus
- StyleTTS 2

## Installation

```bash
pip install ttstune
```

## Development

```bash
pip install uv
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt
pre-commit install
```

## Acknowledgments

TTSTune is built on and wraps the work of many open-source projects. Without them, this project would not be possible.

* [chatterbox-finetuning (@stlohrey)](https://github.com/stlohrey/chatterbox-finetuning)
* [F5-TTS](https://github.com/SWivid/F5-TTS)
* [Unsloth](https://github.com/unslothai/unsloth)

## License

This project is dual-licensed under the MIT and Apache 2.0 licenses. See the [LICENSE.MIT](LICENSE.MIT) and [LICENSE.APACHE](LICENSE.APACHE) files for details.

By submitting contributions, you agree to license your contributions under both licenses.
