Neural audio timbre transfer with RAVE trained on Amen breaks using nn~in Pure Data

Timbre transfer is one of the main use cases for RAVE, “A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling of Artificial Creative Intelligence and Data Science (ACIDS) at IRCAM, Paris. In this video I’m showcasing a RAVE model (V2 architecture, spherical regularization) trained on of Amen break samples. The model loading is done via nn~ object in Pure Data.