SCNet-PyTorch icon indicating copy to clipboard operation
SCNet-PyTorch copied to clipboard

verified publisher icon amanteur
→

Metadata

Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"

Results 2 SCNet-PyTorch issues
Sort by recently updated
recently updated
newest added

Unable to reproduce the results of the paper

16 comment

I tried to train the model, but the average SDR is only about 6. Here are my specific results：

fattyyyyyyyyyy avatar fattyyyyyyyyyy

The sampling rate of the processed song has decreased. Is there any way to restore it to the original sampling rate?

1 comment

![image](https://github.com/user-attachments/assets/c8f7a72c-c414-4a0b-8cff-d186a511779c) ![image](https://github.com/user-attachments/assets/4abc1ba5-5325-45a3-9144-3c22f2ada4b7) The previous image and the next image are the time-frequency image of the original audio and of the separated audio of other, respectively. It is obvious that the...

WayneTan1 avatar WayneTan1

← Metadata

34
Stars
1
Forks
Watchers

Owner

verified publisher icon amanteur

Metadata

Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"

Back