search

facebookresearch / denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
Other
1.65k stars 302 forks source link

Can I use that code on real-time?(by CoLAB) #128

Closed PLEASEHELPMEPEOPLE closed 2 years ago

PLEASEHELPMEPEOPLE commented 2 years ago

Hi, I want to use that in real-time, so I tried to run that program on pycharm(I'm using Windows) but because I'm the beginner of deep learning, it was hard to use it, and there were a lot of errors related to pip and loopback audio interface(at windows, it calls "stereo mix"), so I failed to use it on the window.. I have two questions:

  1. can I use that program on CoLAB for real-time? If it can, it would be really thankful to get that colab link
  2. If I can't, can I get some more.. details about how to use that on pycharm? And is it able to use it on Realtek stereo mix audio?

Thank you for watching my questions, And it would be really grateful to get some your opinion.

PLEASEHELPMEPEOPLE commented 2 years ago

To add more explanation, I installed "Realtek high-definition audio", but it is not visible in the sound setting window. when I list the available audio interfaces with python -m sounddevice, image there were no devices with loopback audio interface..:( after entering python -m denoiser.live --out INDEX_OR_NAME_OF_LOOPBACK_IFACE, Invalid output audio interface INDEX_OR_NAME_OF_LOOPBACK_IFACE. were shown. I'm also curious to select the default device of the sounddevice...