search

openai / jukebox

Code for the paper "Jukebox: A Generative Model for Music"
https://openai.com/blog/jukebox/
Other
7.83k stars 1.41k forks source link

Fine-tuning the prior #282

Open tanner-ducharme opened 1 year ago

tanner-ducharme commented 1 year ago

Does fine-tuning the prior also implicitly train the middle and bottom upsampling layers? Or are those layers left with their pre-trained weights and only the top prior is fine-tuned?

Thanks!