Open to contributions to make this framework bigger and better.

🙏 Thanks to my collaborators @csteinmetz1.bsky.social and Joshua Reiss.

Differentiable DSP processors and controllers for non-parametric and parametric signal chains.

State-of-the-art neural networks and conditioning methods for audio effects modeling.

NablAFx includes all necessary classes to train a model, plot and log losses, metrics and media.

Compared to other frameworks/libraries, NablAFx includes all the building blocks to define, train and evaluate black-box models or gray-box signal chains.

Would love to be added! Thanks for this list.