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
[INSTALLATION PROBLEM] #86
Comments
This is on a Windows 10 install. During install I got this error -- Successfully built librosa soundstretch audioread resampy And later -- Found existing installation: llvmlite 0.29.0 Then it seemed to continue to install correctly & at the very end, uninstalled a couple of older versions of "torch" & "torchvision" & ended with "Successfully installed torch-1.8.1+cu111 torchaudio-0.8.1 torchvision-0.9.1+cu111 typing-extensions-3.10.0.0" After this install & when I run the "python VocalRemover.py" , I get this error message "ModuleNotFoundError: No module named 'cv2'" Thanks for your help, Rog |
run this command pip3 install opencv-python |
I did finally get it running yesterday running "pip3 install opencv-python" + one other install that an error showed up for after this but I now can not get the shortcut to work yet. I have to go through a Anaconda command promp, add the folder that UVR-V4GUI is in, then the UVR-V4GUI & finally the Even changing the line inside the UVR-V4GUI folder to "python VocalRemover.py" will not bring up the GUI interface. Also, is their anyway to get a Radeon RX-550 GPU to work with this to speed it up? Thanks for your help on this, Rog |
Only NVIDIA GPUs that support CUDA are able to use the GPU acceleration. |
For the issues you described, if those are still present after UVR V5 released with the revamped GUI, which is heavily in the works currently, please do not hesitate to create a seperate issue with all the steps to reproduce the issue. |
Dilan, Great to hear you are working on a V5 version & hope it will do some Rog |
I apologize for the incomvenience you have had to face. Support for v4 has dropped as there are currently heavy works for the revamped GUI for v5. This GUI will be much more user-friendly and hopefully easier to set up as well. |
Dilan, No problem. Have you looked at using Open-Unmix UMX for stem separations or using their new added training table as it is giving better results now? A GUI for it would be much appreciated. Rog |
Unfortunately, I do not have any more spare time to work on other projects. |
Dilan, I understand but at least using their new larger training table in your program would likely give better results like open-unmix umx is now giving. The vocals separations with this new version is very good. Rog |
I am only responsible for the GUI |
The current version of the open-unmix cannot be better than the tsurumeso's VR, because it uses several times less computing resources. In addition, VR has one very important advantage. It doesn't require large datasets, which makes it possible to create the Karokee model (it is trained on only 400 pairs and in the case of unmix, this amount would not be enough). |
I want to add just because any vocal seperator does not use as much resources as UVR that does not make it automatically inferior, it could be more efficient!* |
Thanks for your responses & I am looking forward to your updated V5 version soon. Rog |
To Reproduce
On which installation step did you encounter the issue.
Screenshots
Add screenshots to help explain your problem.
Desktop (please complete the following information):
Additional context
Add any other context about the problem here.
The text was updated successfully, but these errors were encountered: