Acoustic guitar separation #593
Answered
by
mpariente
edgarcin95
asked this question in
Q&A
-
|
Hello, I am searching for a good toolkit-library for my project. I want to create a deep learning model that separates an acoustic guitar from a song, so I create my own dataset including the WAV files of the mix and the acoustic guitar for several songs. Is it possible to load my dataset for training in Asteroid? Also I would like to build custom architectures. |
Beta Was this translation helpful? Give feedback.
Answered by
mpariente
Feb 3, 2022
Replies: 1 comment
-
|
Hello, Yes, it is possible. You need to write a custom PyTorch Dataset, and your architecture can use Asteroid's building blocks ! |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
edgarcin95
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello,
Yes, it is possible. You need to write a custom PyTorch Dataset, and your architecture can use Asteroid's building blocks !