rishikksh20/VocGAN

Issues

• Inference speed on CPU

  #8 opened 3 years ago by wizardk
  2

• Can't I change the length of my voice length?

  #32 opened 3 years ago by Koeunseooooo
  1

• KeyError: '__getstate__'

  #16 opened 4 years ago by c1a1o1
  1

• Quality Comparison

  #29 opened 3 years ago by Coice
  1

• Is it possible to train KSS dataset in master branch?

  #27 opened 3 years ago by taewhankim
  2

• JCU Discriminator implementation details

  #26 opened 3 years ago by twinklecc
  0

• validation path and valid data

  #25 opened 3 years ago by twinklecc
  0

• Should there be any changes in the inference code for Korean inputs?

  #23 opened 4 years ago by jodumagpi
  3

• What did you use to generate the mel files from text?

  #21 opened 4 years ago
  1

• [Question] Multi-Speaker Training

  #13 opened 4 years ago by sooftware
  2

• [Question] How to change configuration parameters for 16KHz or 24Khz training data

  #17 opened 4 years ago by twonine1
  3

• [Proposal] Reduce training time by resampling beforehand

  #15 opened 4 years ago by Craq
  1

• Question: validation set size, how many epochs to train?

  #10 opened 4 years ago by domcross
  2

• Any pretrained models?

  #4 opened 4 years ago by Datasciensyash
  2

• Assertion error: torchaaudio resample_waveform related

  #11 opened 4 years ago by raikarsagar
  3

• Metallic / Robotic sound

  #9 opened 4 years ago by Datasciensyash
  1

• Training speed?

  #7 opened 4 years ago by ZDisket
  0

• What major issue are you facing right now?

  #6 opened 4 years ago by charlie-codes-choi
  1