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
1.26k stars 181 forks source link

Invalid argument: num_frames must be -1 or greater than 0. #95

Closed Feavore closed 10 months ago

Feavore commented 1 year ago

i got this issue on training process

TokiFeng1 commented 7 months ago

how did you fix it?

Feavore commented 7 months ago

Hi @TokiFeng1 In my case, i set wrong path to the dset config then catched this error. You should check whether the folder paths in config were correct or json files in that folder were not empty.

mynameiswqq commented 6 months ago

sorry,i can not understand your means,please more details,ok?