crlandsc/torch-l1-snr

Variations of L1 SNR Loss function for training audio source separation machine learning models

42
/ 100
Emerging

This package helps audio engineers and researchers improve the quality of machine learning models for audio source separation. It takes a model's estimated audio components (like vocals or instruments) and the actual, isolated components, then provides a score that helps the model learn to produce clearer separations. This is useful for anyone training models to untangle mixed audio, such as for music production, speech enhancement, or environmental sound analysis.

Available on PyPI.

Use this if you are developing or training machine learning models that need to accurately separate mixed audio signals into their constituent parts.

Not ideal if you are an end-user simply looking to separate audio files without needing to train a custom machine learning model.

audio-separation speech-enhancement music-demixing sound-engineering machine-learning-training
Maintenance 10 / 25
Adoption 8 / 25
Maturity 24 / 25
Community 0 / 25

How are scores calculated?

Stars

43

Forks

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/crlandsc/torch-l1-snr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.