Metadata-Version: 2.4
Name: audio-clean-booster
Version: 0.1.0
Summary: Speech cleanup helpers using open-source enhancers plus reference-guided matching.
Author: audio-clean-booster contributors
License: MIT
Project-URL: Homepage, https://github.com/tchamna/audio-clean-booster
Project-URL: Repository, https://github.com/tchamna/audio-clean-booster
Keywords: audio,speech,denoise,dereverb,enhancement
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: soundfile
Provides-Extra: deepfilter
Requires-Dist: deepfilternet==0.5.6; extra == "deepfilter"
Requires-Dist: noisereduce>=3.0.0; extra == "deepfilter"
Requires-Dist: torch; extra == "deepfilter"
Requires-Dist: torchaudio; extra == "deepfilter"
Provides-Extra: clearvoice
Requires-Dist: clearvoice==0.1.2; extra == "clearvoice"
Provides-Extra: quality
Requires-Dist: noisereduce>=3.0.0; extra == "quality"
Provides-Extra: all
Requires-Dist: clearvoice==0.1.2; extra == "all"
Requires-Dist: deepfilternet==0.5.6; extra == "all"
Requires-Dist: noisereduce>=3.0.0; extra == "all"
Requires-Dist: torch; extra == "all"
Requires-Dist: torchaudio; extra == "all"
Dynamic: license-file

# audio-clean-booster

Open-source speech cleanup helpers for denoising, reference matching, and chunked listening comparisons.

The package can:

- Run DeepFilterNet3 speech denoising.
- Run ClearVoice MossFormer2 speech enhancement.
- Match an enhanced file to a provided clean reference with local loudness, spectral shaping, and strict reference targeting.
- Build an HTML page with 10-second audio chunks for side-by-side comparison.

## Install

Base install:

```bash
pip install audio-clean-booster
```

Install all model backends:

```bash
pip install "audio-clean-booster[all]"
```

For local development:

```bash
pip install -e ".[all]"
```

## CLI

Run DeepFilterNet3:

```bash
acb deepfilter noisy_16k.wav noisy_16k_deepfilter.wav
```

Run MossFormer2:

```bash
acb mossformer noisy_16k.wav noisy_16k_mossformer2.wav
```

Create a strict reference-guided match:

```bash
acb reference-match noisy_16k_mossformer2.wav noisy_16k_clean_original.wav noisy_16k_final.wav --mode strict
```

Build a comparison page:

```bash
acb compare --source noisy:noisy_16k.wav --source mine:noisy_16k_clean_original.wav --source final:noisy_16k_final.wav
```

This writes `compare_chunks.html` and chunk WAV files under `compare_chunks/`.

## Publishing

```bash
python -m build
python -m twine upload dist/*
```

Before publishing, update the `Homepage` and `Repository` URLs in `pyproject.toml`.
