Audio-driven-TalkingFace-HeadPose
Audio-driven-TalkingFace-HeadPose copied to clipboard
How to prepare my own dataset to training? any advice?
I was able to refine the Google Colab demo notebook and got it to work. Not only on the preset audio and video files from the notebook, but also my own audio and video files. Is that what you mean by your own dataset to train?
I was able to refine the Google Colab demo notebook and got it to work. Not only on the preset audio and video files from the notebook, but also my own audio and video files. Is that what you mean by your own dataset to train? Could you please tell me how to run this Colab demo? Directly running
pip install -r requirements_colab.txt
caused many packages version conflicts. Thanks.