search

shahules786 / mayavoz

Pytorch based speech enhancement toolkit.
MIT License
328 stars 21 forks source link

Enhanced speech from pretrained DCCRN #49

Open mystlee opened 1 year ago

mystlee commented 1 year ago

Hi, I used your pretrained DCCRN, but there are some problem

First, it requires 2 seconds longer signal And, the output value are NaNs I tried with sample audio in tests/data/vctk. And my environment is titanX with cuda 11.4 with torch==1.12.1+cu113

waveunet and demucs are working well

shahules786 commented 1 year ago

@mystlee Thanks for reporting the error and feel free to send a PR if you're working on it:)