Edit model card

Musika Techno Model

Pretrained Techno GAN model for the Musika system for fast infinite waveform music generation. Introduced in this paper.

Model description

This pretrained GAN system consists of a ResNet-style generator and discriminator. During training, stability is controlled by adapting the strength of gradient penalty regularization on-the-fly. The gradient penalty weighting term is contained in switch.npy. The generator is conditioned on a latent coordinate system to produce samples of arbitrary length. The latent representations produced by the generator are then passed to a decoder which converts them into waveform audio. The generator has a context window of about 12 seconds of audio.

How to use

This pretrained Techno GAN system is automatically downloaded at the first execution of the system. Try Musika here!

Training data

The Techno GAN system was trained on 1000 hours of music with the techno tag from jamendo.com.

Downloads last month
Unable to determine this model’s pipeline type. Check the docs .