Any volunteers for lipsync via tensorflow and opencv?

Hi folks,

Saw yesterday on Twitter a retweet from @dceejay about LipSync. From their Github page, it seems that there is a Tensorflow FaceMesh model available. I assume that can be used in node-red via the node-red-contrib-tf-model node? And then they do some processing via OpenCV matchShapes.

I think this might be a fun Node-RED project, to implement e.g. voice recognition based on webcam images. So using images instead of audio...

I'm not experienced with the Tensorflow and OpenCv matchShapes stuff, so I was wondering if there is anybody in the community that has enough time and knowledge to experiment with this ...

And of course if some extra nodes are required for this, I will pop in :wink:


1 Like

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.