Musika Model: yellow-magic-orchestra-2

Model provided by: nobitachainsaw

Pretrained yellow-magic-orchestra-2 model for the Musika system for fast infinite waveform music generation. Introduced in this paper.

How to use

You can generate music from this pretrained yellow-magic-orchestra-2 model using the notebook available here.

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. This model is learning the songs of the techno band "Yellow Magic Orchestra" commonly known as YMO, which was born in Japan in 1978. The learning data is about 17 songs.

Bug: Probably because there is little learning data, the completeness is not very good. However, the sound of Yukihiro's drum seems to be highly reproducible.

Postscript: This model is still in the experimental stage. There may be other improvements in the future.

This explanation is translated through Google Translate.