facebookresearch / svoice

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
Other
1.25k stars 179 forks source link

Function 'DivBackward0' returned nan values in its 1th output #78

Open fabianoluzbr opened 2 years ago

fabianoluzbr commented 2 years ago

Hi folks,

I got this error here:

python3.8/site-packages/torch/autograd/__init__.py", line 130, in backward Variable._execution_engine.run_backward( RuntimeError: Function 'DivBackward0' returned nan values in its 1th output.

After executing this line of code:

svoice/svoice/solver.py", line 217, in _run_one_epoch loss.backward() Can anyone help me with this?

desperado1999 commented 1 year ago

Same error. I am training svoice on Libri4Mix dataset, and the error outputs are the same

qalabeabbas49 commented 1 year ago

any solution to this?