marcop commited on
Commit
93a17d8
1 Parent(s): c72074c

add model card

Browse files
Files changed (2) hide show
  1. README.md +25 -0
  2. README.md.backup +28 -0
README.md CHANGED
@@ -1,3 +1,28 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ library_name: keras
4
+ tags:
5
+ - audio
6
+ - music
7
+ - generation
8
+ - tensorflow
9
  ---
10
+
11
+ # Musika Misc Model
12
+
13
+ Pretrained Misc GAN 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
+ ## Model description
17
+
18
+ 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.
19
+ The generator has a context window of about 12 seconds of audio.
20
+
21
+ ### How to use
22
+
23
+ This pretrained Misc GAN system is automatically downloaded at the first execution of the system. Try Musika [here](https://github.com/marcoppasini/musika)!
24
+
25
+
26
+ ## Training data
27
+
28
+ The Misc GAN system was trained on the SXSW music dataset (17000 songs with diverse genres).
README.md.backup ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: keras
4
+ tags:
5
+ - audio
6
+ - music
7
+ - generation
8
+ - tensorflow
9
+ ---
10
+
11
+ # Musika Misc Model
12
+
13
+ Pretrained Misc GAN 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
+ ## Model description
17
+
18
+ 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.
19
+ The generator has a context window of about 12 seconds of audio.
20
+
21
+ ### How to use
22
+
23
+ This pretrained Misc GAN system is automatically downloaded at the first execution of the system. Try Musika [here](https://github.com/marcoppasini/musika)!
24
+
25
+
26
+ ## Training data
27
+
28
+ The Misc GAN system was trained on the SXSW music dataset (17000 songs with diverse genres).