daniilrobnikov/vits2

Issues

• Multi-speaker training

  #15 opened 4 months ago by pengpengtao
  0

• What version of torch？

  #8 opened a year ago by aijianiula0601
  2

• ModuleNotFoundError | Step 4 of Custom Dataset

  #7 opened a year ago by 641i130
  5

• Model Weights

  #14 opened 7 months ago by chiragoel
  0

• Can I copy vocab.txt from ljs_base to vctk? How to preprocess text in vctk?

  #13 opened 8 months ago by Jianshu1only
  0

• How much computing resources are needed for training?

  #12 opened 10 months ago by Frei2
  0

• normalize_flow 和官方VITS代码不一样的实现方式

  #6 opened a year ago by nzpeng
  2

• espeak phoneme tokenization - failed experiment?

  #11 opened a year ago by Teravus
  0

• Should z_q_dur drawn from Gaussian distribution?

  #10 opened a year ago by trinh-hoang-hiep
  0

• faster?

  #9 opened a year ago by foocker
  0

• Anyone working on a German vits2?

  #5 opened a year ago by paperr0se
  3

• n_speakers > 0 有问题啊兄弟

  #2 opened a year ago by wlz987
  3

• DistributedBucketSampler division by zero problem

  #4 opened a year ago by y1guo
  1

• Hi, does there any Chinese support?

  #1 opened a year ago by lucasjinreal
  12

• AssertionError: min value is nan

  #3 opened a year ago by wlz987
  5