search

fangwei123456 / spikingjelly

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
https://spikingjelly.readthedocs.io
Other
1.4k stars 244 forks source link

Feature extraction for Audio visual speech separation #464

Open SutirthaChakraborty opened 12 months ago

SutirthaChakraborty commented 12 months ago

Hi, I am a newbie, and I want to know how can I use this library to extract the visual facial embedding of videos so that I can use it for a real-time speech separation model so that it have the temporal information.

fangwei123456 commented 12 months ago

Hi, I do not know much about the visual facial embedding of videos. You can read the tutorials of SpikingJelly and see if they are helpful.