vskadandale/vocalist

Issues

• Used with wav2lip?

  #18 opened 9 months ago by constan1
  0

• Acappella

  #15 opened a year ago by NicholasLiuSc
  0

• model output range question

  #14 opened a year ago by ketyi
  0

• Having some gaps in understanding the working of the code.

  #13 opened a year ago by AmanSavaria1402
  0

• Getting the acappella dataset.

  #12 opened a year ago by AmanSavaria1402
  0

• Dataset

  #10 opened a year ago by ZZ00325
  0

• The label of Dataset

  #11 opened a year ago by ZZ00325
  0

• Loss not decreasing on increasing time step

  #9 opened 2 years ago by agupta54
  0

• Why is the test result not an image or video?

  #6 opened 2 years ago by c1a1o1
  1

• About training loss on my custom datasets

  #8 opened 2 years ago by QUTGXX
  0

• Inference on custom audio and video.

  #7 opened 2 years ago by rohaantahir
  0

• 4: Padding size should be less than the corresponding input dimension, but got: padding (400, 400) at dimension 2 of input [1, 191488, 2]

  #2 opened 2 years ago by c1a1o1
  1

• Can the test result be a video?

  #4 opened 2 years ago by c1a1o1
  1

• The test result is the accuracy? ?

  #3 opened 2 years ago by c1a1o1
  1

• Question of Evaluation protocol

  #5 opened 2 years ago by LeeJ1Hyun
  1

• Code and weights release

  #1 opened 3 years ago by mittalgovind
  2