demucs help

[kth2265426]

❓ Questions

I installed Python 3.10.0 on my laptop, installed ffmpeg, set the paths for each, and installed the latest versions of demucs and torchaudio. I tried to separate vocals from a wav file, but I keep getting the following message and it doesn't work. Despite numerous attempts to fix the errors with the help of AI like ChatGPT, I keep getting the same result dozens of times. What is the problem and how can I fix it? Please help.

File "c:\Vpan\demucs_env\lib\site-packages\torchaudio_backend\utils.py", line 222, in dispatcher raise RuntimeError(f"Couldn't find appropriate backend to handle uri {uri} and format {format}.") RuntimeError: Couldn't find appropriate backend to handle uri separated\htdemucs_ft\song-I16\drums.wav and format None.

[CarlGao4]

First of all, demucs only supports PyTorch < 2.2 so you may need to downgrade your PyTorch
Then, if the error still occurs, please make sure that you've installed soundfile (pip install soundfile)
Finally, you can use the GUI version at CarlGao4/Demucs-Gui