Neural audio music style transfer with RAVE using nn~ in Pure Data
In this video I’m showcasing a RAVE model that has been trained on a dataset consisting of Martsman material pre 2010 (subjectively heterogenous) using the V2 architecture and ELBo regularization.
The input is a stand alone break beat and I’m manipulating the latent vectors with different techniques. Model loading is done via nn~ object in Pure Data.
RAVE, is “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.
nn~ on GitHub:
1 view
249
64
3 months ago 00:59:48 1
[1hr Talk] Intro to Large Language Models
3 months ago 00:32:32 1
The future of AI looks like THIS (& it can learn infinitely)
3 months ago 00:01:00 1
1 Minute 7 Chakra Balancing & Healing | “Boost Your Aura“ | Attract Positive Energy
3 months ago 00:04:03 2
The Battle of Agincour - Sergei Galkin and Udio
3 months ago 00:11:07 1
The Most ROCKIN’ Marshall Plugin?
3 months ago 00:14:58 2
Plini - Electric Sunrise, I’ll Tell You Someday, Cascade | Live at Finnvox Studios
3 months ago 00:03:23 1
10 Levels Of THALL
3 months ago 00:09:29 6
Ограбление по числам.Н6вый зак6н о прир6сте капитала
3 months ago 00:10:19 1
Is the Intelligence-Explosion Near? A Reality Check.
4 months ago 00:04:52 1
Sway & King Tech – The Anthem (ft. RZA, Tech N9ne, Eminem, Xzibit & KRS-One) (Explicit) [HD] (1999)
4 months ago 00:09:09 1
Backbone 1.5 and DrumGAN by Sony Computer Science Laboratory | Walkthrough