Upload bullerengue-beta readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- audio
|
| 5 |
+
- music
|
| 6 |
+
- generation
|
| 7 |
+
- tensorflow
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Musika Model: bullerengue-beta
|
| 11 |
+
## Model provided by: frncscp
|
| 12 |
+
|
| 13 |
+
Pretrained bullerengue-beta model for the [Musika system](https://github.com/marcoppasini/musika) for fast infinite waveform music generation.
|
| 14 |
+
Introduced in [this paper](https://arxiv.org/abs/2208.08706).
|
| 15 |
+
|
| 16 |
+
## How to use
|
| 17 |
+
|
| 18 |
+
You can generate music from this pretrained bullerengue-beta model using the notebook available [here](https://colab.research.google.com/drive/1HJWliBXPi-Xlx3gY8cjFI5-xaZgrTD7r).
|
| 19 |
+
|
| 20 |
+
### Model description
|
| 21 |
+
|
| 22 |
+
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.
|
| 23 |
+
The generator has a context window of about 12 seconds of audio.
|