descriptinc/cargan

Issues

• How to generate speech at 16kHz?

  #16 opened a year ago by ahmed-fau
  1

• inference speed

  #6 opened 2 years ago by forwiat
  2

• Training models with 24000 Hz audio data

  #10 opened 2 years ago by zerlinwang
  3

• TypeError: can't convert np.ndarray of type numpy.uint16.

  #11 opened 2 years ago by zerlinwang
  3

• How do i train my own model？

  #5 opened 2 years ago by c9412600
  1

• colab

  #3 opened 2 years ago by AK391
  2

• Versions of torch and torchaudio to use on Colab?

  #14 opened 3 years ago by rohitgupta3
  0

• Pitch Losses

  #13 opened 3 years ago by Whyki
  2

• Poor results on Mandarin singing voice data

  #12 opened 3 years ago by WelkinYang
  1

• Train model by 24k

  #9 opened 3 years ago by zerlinwang
  0

• Discriminator weights

  #8 opened 3 years ago by pranavmalikk
  0

• about the ar loop?

  #7 opened 3 years ago by azraelkuan
  2

• Will discriminator weights be released?

  #4 opened 3 years ago by PluieElectrique
  3

• Pip package is missing submodules

  #2 opened 3 years ago by PluieElectrique
  1