marcoppasini/MelGAN-VC

Issues

• Issue with pre-processing the dataset

  #23 opened 10 months ago by charvibannur
  4

• Upgrade Issue when upgrading to Torchaudio > 0.5.0?

  #21 opened 2 years ago by ark626
  2

• Does the notebook not work anymore?

  #22 opened 2 years ago by WinWut
  1

• numpy.random._bounded_integers._rand_int64 ValueError: high <= 0

  #20 opened 3 years ago by sirius0503
  0

• RuntimeError: mat1 and mat2 shapes cannot be multiplied (282x577 and 201x192)

  #19 opened 3 years ago by morganne00
  4

• where is the pretrain model?

  #18 opened 3 years ago by saleh73
  0

• How to achieve better generalization from unseen source audio inputs?

  #16 opened 4 years ago by moiseshorta
  5

• Metalic voice

  #14 opened 4 years ago by Dannynis
  1

• How to create audio style transfer

  #17 opened 4 years ago by berend-tol
  0

• Results: MelGAN-VC generated music

  #12 opened 5 years ago by moiseshorta
  3

• Bare minimum code for inference only?

  #15 opened 4 years ago by AndroYD84
  0

• hop_length

  #11 opened 5 years ago by CarolinGao
  1

• Nice to have a requirements.txt

  #10 opened 5 years ago by MohitB9
  1

• Request for link to pretrained models

  #8 opened 5 years ago by FarisHijazi
  1

• does dsa correspond to dsb

  #9 opened 5 years ago by tuanad121
  1

• Would you please explain the inference process and what does GRAD do?

  #2 opened 5 years ago by youngsuenXMLY
  3

• Is it possible that I convert it to realtime model?

  #7 opened 5 years ago by CarolinGao
  1

• Distorted/clipping outputs in generated audio

  #6 opened 5 years ago by moih
  3

• Possible to generate new sounds from latent space

  #5 opened 5 years ago by moih
  1

• Recommended amount of audio data for target and source audio

  #4 opened 5 years ago by moih
  1

• Does the method support other languages?

  #3 opened 5 years ago by CarolinGao
  1

• What tensorflow version does this project use?

  #1 opened 5 years ago by youngsuenXMLY
  1