Metadata-Version: 2.4
Name: vst-bench-ml
Version: 0.1.1
Summary: Auditable audio-plugin dataset generation and offline integrity verification
Project-URL: Homepage, https://github.com/itsuzef/vst-bench-ml-public
Project-URL: Documentation, https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/README.md
Project-URL: Repository, https://github.com/itsuzef/vst-bench-ml-public
Project-URL: Issues, https://github.com/itsuzef/vst-bench-ml-public/issues
Project-URL: Changelog, https://github.com/itsuzef/vst-bench-ml-public/blob/main/CHANGELOG.md
Author: Youssef Hemimy
License-Expression: MIT
License-File: LICENSE
License-File: NOTICE
Keywords: audio,dataset,plugin,provenance,rendering
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Multimedia :: Sound/Audio
Classifier: Topic :: Scientific/Engineering
Requires-Python: >=3.10
Requires-Dist: numpy==2.2.6
Requires-Dist: pyloudnorm==0.1.1
Requires-Dist: soundfile==0.13.1
Provides-Extra: dev
Requires-Dist: hatchling==1.27.0; extra == 'dev'
Requires-Dist: pytest==8.4.1; extra == 'dev'
Requires-Dist: ruff==0.12.0; extra == 'dev'
Description-Content-Type: text/markdown

# vst-bench-ml

Generate audio-plugin datasets with records of how each output was produced.
`vst-bench-ml` samples plugin parameters, coordinates offline rendering, records
software and render settings, and checks stored artifacts for changes or missing files.

## Install

Use Python 3.12 in a virtual environment:

```sh
python3.12 -m venv .venv
source .venv/bin/activate
python -m pip install vst-bench-ml==0.1.1
vst-bench-ml --help
```

Alternatively, install a source checkout with `python -m pip install .`.

The metadata permits Python 3.10 or newer. The documented rendering environment
is macOS arm64 with Python 3.12; see the installation guide for the tested scope.

## First dataset

Rendering needs a separately installed host and a plugin. The
[sample-free companion walkthrough](https://github.com/itsuzef/vst-bench-dataset-host-public/blob/main/docs/QUICKSTART.md)
provides both and takes you from installation to eight small generated outputs.
The broader `vst-bench` MCP testing application is not required.

For a configured compatible host:

```sh
vst-bench-ml render --plugin /absolute/path/to/example.vst3 \
  --param-manifest parameter-manifest.json --n 4 --out output \
  --seed-label example-v1
vst-bench-ml verify --manifest output/manifest.json
```

Use a new output directory and a fresh host for each render. Offline verification
needs only this Python package and the stored dataset, without running a plugin.

## Learn more

- [User documentation](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/README.md)
- [Installation](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/INSTALL.md)
- [Commands and outputs](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/USAGE.md)
- [Troubleshooting](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/TROUBLESHOOTING.md)
- [Architecture and host protocol](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/DESIGN.md)
- [Issues](https://github.com/itsuzef/vst-bench-ml-public/issues) and [contributing](https://github.com/itsuzef/vst-bench-ml-public/blob/main/CONTRIBUTING.md)

The package contains Python tools; the host, plugin binaries, datasets, presets,
and audio are supplied or generated separately. Hashes establish artifact
integrity. Matching output bytes have only been demonstrated on pinned environments;
scientific suitability and cross-platform audio identity require separate evaluation.

## Source, licence, and citation

MIT source; dependency notices are in [NOTICE](https://github.com/itsuzef/vst-bench-ml-public/blob/main/NOTICE).
The [0.1.0 Zenodo archive](https://doi.org/10.5281/zenodo.22924036) remains the
historical release. See [public source history](https://github.com/itsuzef/vst-bench-ml-public/blob/main/docs/HISTORY.md)
and [CITATION.cff](https://github.com/itsuzef/vst-bench-ml-public/blob/main/CITATION.cff) for version-specific attribution.
