Doubiiu / CodeTalker

[CVPR 2023] CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior
MIT License
515 stars 57 forks source link

A typo in vocaset stage2.yaml? What is "wav_mini"? #59

Closed YifengMa9 closed 12 months ago

YifengMa9 commented 12 months ago

Thanks for your remarkable work.

In stage2.yaml

DATA:
  dataset: vocaset
  data_root: ./vocaset/
  wav_path: wav_mini
  vertices_path: vertices_npy

Should wav_path be wav, not wav_mini ?

Doubiiu commented 12 months ago

Thanks for your pointing out. It is a typo, and should be wav. wav_mini is a subset for saving dataloading time and debugging.