VCTK dataset v0.92 not compatible with current training pipeline/scripts

facebookresearch / speech-resynthesis

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Other

390 stars 54 forks source link

VCTK dataset v0.92 not compatible with current training pipeline/scripts #3

Closed slegroux closed 3 years ago

slegroux commented 3 years ago

The link to VCTK dataset mentioned in the README (https://datashare.ed.ac.uk/handle/10283/3443) points to version 0.92, which content doesn't correspond to the file paths provided in datasets/VCTK/cpc100/train.txt (VCTK 0.92 contains 2 mic recordings mic1, mic2 in Flac format. which mic should we use? or should we combine them?)

adiyoss commented 3 years ago

Right! good catch :) We will update these code ASAP Thanks!

adampolyak commented 3 years ago

Hi,

We updated the preprocess scripts and codes for VCTK 0.92. Thanks!

slegroux commented 3 years ago

Awesome. Thank you! will give it a try.