Open SullyMan71 opened 1 year ago
I'm facing the same issue, have you managed to solve it yet?
Facing the same issue on Google Colab:
with HP-4BAND-V2_arch-124m.pth
loading model... done
stft of wave source... Traceback (most recent call last):
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 307, in
A Google Colab update must've broken something.
Something to do with arguments that spec_utils.py is taking . can't really understand the code :\
I was having the same problem, but found a solution on Discord (posted by Gosmokeless28)
Put
!pip install librosa==0.9.1
in the audio separation cell of the UVR 5.2 Colab notebook
I did it and now it works. I had to copy the Colab project first, to be able to edit the code. Then I added a new code under the first cell (under the cell where you mount your GDrive account) and included the pip install code mentioned. Also, upon running the first cell, I checked the box "ForceUpdate", which I think pulls the latest version of the git project, I guess that's important too. It works!
Window size: 320 Model: HP2-4BAND-3090_4band_arch-500m_2 Parameter: 4band_44100 Aggressiveness: 0.09 High end process: mirroring2 TTA: True Deep Extraction: False
loading model... done stft of wave source... Traceback (most recent call last): File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 307, in
main()
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 302, in main
process.inference()
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 94, in inference
X_spec_m, input_high_end_h, input_high_end = spec_utils.loadWave(self.input, mp, hep=self.hep)
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/lib/spec_utils.py", line 14, in loadWave
X_wave[bandsn+1], = librosa.load(
TypeError: load() takes 1 positional argument but 3 positional arguments (and 2 keyword-only arguments) were given
Notebook took: 8.3s