Trying out unusual genre combinations with OpenAI Jukebox

Join the Jukebox community at https://discord.gg/aEqXFN9amV

The Big Sleep Colab notebook: https://colab.research.google.com/drive/1Q2DIeMqYm_Sc5mlurnnurMMVqlgXpZNO?usp=sharing

FAQ:

• What is OpenAI Jukebox?
Simply put, it's a neural net that generates music - read more about it on the official blog: https://openai.com/blog/jukebox/

• Can I use Jukebox myself?
Yes! If you have a very powerful graphics unit (at least 16GB of VRAM for the 5b_lyrics model), you can run Jukebox through Python. If you don't, you can give Google Colab a try.

• Is there a tutorial?
Yes, I made a tutorial explaining the basics about generating samples and upsampling through Google Colab. https://youtu.be/PXxGOl-ATa4

• What has Jukebox been trained on?
According to OpenAI, it has been trained on 1.2 million songs. Unfortunately, OpenAI has not publicly disclosed which songs are in this dataset.

• What sampling temperature are you using?
Always between .975 and 1 - Usually .98

#openaijukebox
#jukeboxai

0:00 Medieval Jazz #1
1:04 Death Salsa #1
2:15 Classical Gangsta #1
3:26 Gospel Metal #1
4:38 Christian Trance #1
5:43 Medieval Jazz #2
6:48 Death Salsa #2
7:59 Classical Gangsta #2
8:51 Gospel Metal #2
10:00 Christian Trance #2
11:08 Medieval Jazz #3
12:15 Death Salsa #3
13:11 Christian Trance #3
14:16 Bonus (Death Salsa #4)

Видео Trying out unusual genre combinations with OpenAI Jukebox канала Broccaloo