FENRlR/MB-iSTFT-VITS2

Issues

• How to go ahead by adding emotion as a trainable parameter?

  #21 opened 5 months ago by debasish-mihup
  2

• AttributeError: 'ResidualCouplingTransformersLayer2' object has no attribute 'remove_weight_norm'

  #18 opened 5 months ago by Serdcoff
  1

• My experience and pronunciation problems

  #20 opened 5 months ago by bzp83
  1

• KSS dataset for 490 epochs but the quality is not as good as I expected

  #4 opened a year ago by ggpid
  6

• Would it be possible to train and initialize training with previous checkpoint?

  #16 opened 7 months ago by debasish-mihup
  8

• Comparative Analysis and Training Results of VITS2 with HifiGAN, iSTFT and BigVGAN

  #2 opened a year ago by shigabeev
  8

• rank error

  #15 opened a year ago by zhanglina94
  2

• Boolean value subbands in istft_vits2_base.json?

  #14 opened a year ago by isdanni
  2

• Multispeaker training issue

  #13 opened a year ago by kafan1986
  3

• Training more Chinese speaking person error: ValueError: too many values to unpack (expected 3)

  #12 opened a year ago by Bohemian-self
  2

• Does batch size make a difference to end quality?

  #5 opened a year ago by DavidNTompkins
  2

• ONNX format

  #3 opened a year ago by AigizK
  3

• “ZeroDivisionError: integer division or modulo by zero” in Google Colab

  #8 opened a year ago by Bohemian-self
  2

• ValueError: too many values to unpack (expected 2)

  #9 opened a year ago by KevinWang676
  1

• The model for Chinese speech doesn't work after training for 1700 epochs

  #7 opened a year ago by KevinWang676
  3

• New feature: Deleting the previous .pth files when training

  #6 opened a year ago by KevinWang676
  0