This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
I have read the previous comments about fixing the requirements txt. Here was my experience and I hope this helps others.
These are the issues I ran into:
ERROR: Could not find a version that satisfies the requirement opencv-python==4.1.0.25
ERROR: No matching distribution found for opencv-python==4.1.0.25
After installing opencv I ran into further errors (similar as above) trying to install torch 1.1.0 and torchvision. I messed around with trying to install the torch packages with 'wheel' manually (which didn't work).
My solution and I hope this helps others was to downgrade to python 3.6.
Install Anaconda
Created a virtual environment (so that I didn't have 3.6 running everywhere else, although this is not really necessary).
conda install python=3.6
Check the version to ensure you have 3.6 python3 --version
I have read the previous comments about fixing the requirements txt. Here was my experience and I hope this helps others.
These are the issues I ran into:
After installing opencv I ran into further errors (similar as above) trying to install torch 1.1.0 and torchvision. I messed around with trying to install the torch packages with 'wheel' manually (which didn't work).
My solution and I hope this helps others was to downgrade to python 3.6.
conda install python=3.6
python3 --version
I hope this helps.