search

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
1.23k stars 178 forks source link

RuntimeError: stack expects each tensor to be equal size #72

Closed mirosakr closed 2 years ago

mirosakr commented 2 years ago

I got an error during validation process RuntimeError: stack expects each tensor to be equal size, but got [56000] at entry 0 and [27411] at entry 3 Any help would be appreciated.

fabianoluzbr commented 2 years ago

@mirosakr I have the same problem. you found a solution ?

mirosakr commented 2 years ago

@mirosakr I have the same problem. you found a solution ?

I checked the json file and found that one Id is different in s1 than s2 and mix (they weren't same time) when I updated them to be same time (for s1,s2&mix) the error solved

fabianoluzbr commented 2 years ago

Exactly, thank you!