search

vivjay30 / Cone-of-Silence

The Cone of Silence:
MIT License
151 stars 22 forks source link

dataset used for COS #4

Closed KillerStrike17 closed 4 years ago

KillerStrike17 commented 4 years ago

Hey, I loved your work, I was trying to replicate it, to do that I was generating some synthetic dataset but got some errors and doubts. As you mentioned the dataset used is VCTK, it has dataset in .flac format which is not recognized by the program, so did you guys did any preprocessing over the dataset? And there is no data folder in the original dataset i,e. VCTK (mentioned in the command to generate synthetic dataset). And can you share the dataset you guys used for training?

vivjay30 commented 4 years ago

Hi, the VCTK dataset is actually in .wav format. You'll need to download that from their website. However if you would like to change the file extension used in this library, you can modify this line of the dataset generator: https://github.com/vivjay30/Cone-of-Silence/blob/7108fc07c387ca94e3c399a7da41737307388194/cos/generate_dataset.py#L201