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

SampleVAE Basics notebook fails on import librosa? #24

Open
kcrosley-leisurelabs opened this issue Apr 11, 2022 · 2 comments
Open

SampleVAE Basics notebook fails on import librosa? #24

kcrosley-leisurelabs opened this issue Apr 11, 2022 · 2 comments

Comments

@kcrosley-leisurelabs
Copy link

HI Max (and anyone),

When I attempt to run the SampleVAE Basics notebook, I get the following error on the 5th cell:

image

I'm not sure how to rectify that? Anybody who's not a noob at this sort of thing know? (Yes, I've searched Google and it doesn't really help me.)

Thanks,
K

@kcrosley-leisurelabs
Copy link
Author

Well, I got the notebook working in colab (manually installing some packages, fixing some path issues), but the results of training are pretty disappointing. Everything generated more-or-less just sounds like modulated white noise. (I find this with model_general as well.) Also, there's a lot of amplitude modulation in the generated files as noted in this issue.

Does anyone have any suggestions on different params settings or other changes to get more musical results (when training on pitched content)?

@vespas69
Copy link

Refer to numba/numba#5974

from numba.decorators import jit as optional_jit
->
from numba.core.decorators import jit as optional_jit

The conflict is created in librosa/util/decorators.py & changing it manually solves the problem :)

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

2 participants