Skip to content

Latest commit

 

History

History
15 lines (10 loc) · 619 Bytes

README.md

File metadata and controls

15 lines (10 loc) · 619 Bytes

Pytorch implementation of the paper "Real Time Speech Enhancement in the Waveform Domain"

Installation

Use pytorch version 1.4.0

Create .npy files for the dataset OR load the dataset using a dataloader from a directory. VCTK Dataset (28spk) train/valset .npy present here along with a few pretrained models.

To be implemented:

  1. Normalising the input by standard deviation
  2. Upsampling the waveform by a factor before feeding to a network.

License

MIT