Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature Request: Tensorflow 2.x Support #33

Open
paulreimer opened this issue Mar 29, 2021 · 2 comments
Open

Feature Request: Tensorflow 2.x Support #33

paulreimer opened this issue Mar 29, 2021 · 2 comments

Comments

@paulreimer
Copy link

I think Tensorflow 2.x is officially supported by upstream spleeter as of ~Oct 2020:
deezer/spleeter#498

I'm not fully familiar with how the pieces fit together, but as an Apple Mac M1 user, I think I (currently) need to use a special drop-in compatible version of Tensorflow 2.x, as otherwise I get illegal hardware instruction errors with the current TF 1.x usage:
https://github.com/apple/tensorflow_macos

@PRPoundSix
Copy link

It will be nice to get this updated so we can use the newer model data from Spleeter.

@SuperKogito
Copy link

on an i7-cpu on Windows, I am able to use the Tensorflow version 2.9.0 without needing to change anything in the code. However, I haven't notice any acceleration in the processing.
Which new models are you referring to here btw? the only pre-trained ones available on the official Spleeter page are from 2019. Are referring to models you trained yourself?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants