husher bundles a frozen subset of the Music-Source-Separation-Training
framework by Roman Solovyev (ZFTurbo).

Upstream:
    https://github.com/ZFTurbo/Music-Source-Separation-Training

Bundled subset (under husher/_vendor/mss_training/):
    - models/bandit_v2/        (Bandit v2 model implementation)
    - utils/settings.py        (slim adaptation: load_config and the
                                bandit_v2 branch of get_model_from_config)

The upstream framework is licensed under the MIT License. See the
LICENSE file in this directory for the full upstream copyright notice.
The bundled subset is redistributed under the same MIT License terms.
