search

Rudrabha / Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"
MIT License
692 stars 152 forks source link

Bug in multispeaker branch #13

Closed miraodasilva closed 4 years ago

miraodasilva commented 4 years ago

Hi,

I came across a bug when preprocessing LRW, where ffmpeg fails silently. I'm pretty sure this line https://github.com/Rudrabha/Lip2Wav/blob/a5835ffbaf8d0e13e4ea3b2c391618ffd9cc26bd/preprocess.py#L63 should be changed to command = template2.format(vfile, wavpath). This is what worked for me.

By the way, are you planning to release test samples/checkpoints for GRID/TCD-TIMIT. This would be great so that we can compare accurately with your work.

Thanks a lot in advance!

Rudrabha commented 4 years ago

Hello,

Thanks for pointing the mistake out. I have corrected it. We do not plan to release the models for GRID and TIMIT at the moment. If we do so, we will definitely notify you.