More AI drones with vschaos2 neural audio synthesizer (Kerner model)

In this video I'm showcasing a generative setup in Pure Data using neural audio synthesis in the form of a vschaos2 model trained on my 2018 album "Kerner" and simple probability settings that alter signal values of latent vectors.
vschaos2 is a vintage-flavoured neural audio synthesis package by Axel Chemla Romeu Santos. It is based on unsupervised/ (semi-)supervised training of spectral information using variational auto-encoders.
vschaos2 on GitHub: github.com/acids-ircam/vschaos2
nn~ on GitHub: github.com/acids-ircam/nn_tilde
To train models with vschaos2, you can use a Kaggle notebook I've published: github.com/devstermarts/Noteb...