Metadata-Version: 2.4
Name: librosax
Version: 0.1.2
Summary: A JAX implementation of librosa, TorchLibrosa, and nnAudio
Home-page: https://github.com/DBraun/librosax
Author: David Braun
Author-email: David Braun <braun@ccrma.stanford.edu>
License: ISC
Project-URL: Homepage, https://github.com/DBraun/librosax
Project-URL: Issues, https://github.com/DBraun/librosax/issues
Keywords: audio,machine learning,jax
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: ISC License (ISCL)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: einops>=0.8.1
Requires-Dist: flax>=0.12.0
Requires-Dist: jax>=0.8.0
Requires-Dist: librosa>=0.11.0
Requires-Dist: numpy>=2.1.3
Requires-Dist: scipy>=1.16.2
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: torch; extra == "dev"
Requires-Dist: torchlibrosa; extra == "dev"
Provides-Extra: docs
Requires-Dist: sphinx>=4.0; extra == "docs"
Requires-Dist: furo; extra == "docs"
Requires-Dist: m2r2; extra == "docs"
Requires-Dist: sphinx-autobuild; extra == "docs"
Dynamic: license-file

# librosax

A [JAX](https://docs.jax.dev/en/latest/)/[Flax](https://flax.readthedocs.io/en/latest/) implementation of audio processing functions, inspired by and building upon [librosa](https://github.com/librosa/librosa) and [TorchLibrosa](https://github.com/qiuqiangkong/torchlibrosa).

## Installation

Although, it is optional, we recommend first installing the [jax-ai-stack](https://github.com/jax-ml/jax-ai-stack) with one of these three options:

```bash
pip install jax-ai-stack              # JAX CPU
pip install jax-ai-stack "jax[cuda]"  # JAX + AI stack with GPU/CUDA support
pip install jax-ai-stack "jax[tpu]"   # JAX + AI stack with TPU support
```

**Required**: Then install librosax:

```bash
pip install librosax
```

## Documentation

Documentation is [here](http://dirt.design/librosax).

## Acknowledgments

This library is heavily inspired by and borrows code from:

- **[librosa](https://github.com/librosa/librosa)** - The excellent Python library for audio and music analysis by the librosa development team
- **[TorchLibrosa](https://github.com/qiuqiangkong/torchlibrosa)** - PyTorch implementations of librosa functions and neural net layers by Qiuqiang Kong
- **[nnAudio](https://github.com/KinWaiCheuk/nnAudio)** - PyTorch implementations of CQT and other functions by Kin Wai Cheuk

## License

librosax is licensed under the ISC License, matching the license used by librosa. See the [LICENSE](LICENSE) file for details.
