anonymous-pits/pits

Issues

• Can I control the pitch of each phoneme separately?

  #5 opened 2 years ago by majo711
  1

• Trying ot use pitch predictor with different texts.

  #29 opened a year ago by ljh0412
  4

• Phonemes for training

  #27 opened a year ago by JoanisTriandafilidi
  1

• Question about pitch encoder

  #28 opened a year ago by ljh0412
  2

• voice conversion

  #25 opened a year ago by p0p4k
  2

• Training with my own Korean dataset

  #21 opened a year ago by myyhlee
  3

• Artificial noise

  #24 opened a year ago by gandolfxu
  1

• The synthesized speech sounds strange.

  #23 opened a year ago by howitry
  4

• how can the config.yaml file's params change?

  #22 opened a year ago by fangg2000
  1

• mat1 and mat2 shapes cannot be multiplied

  #20 opened a year ago by ppisljar
  2

• How to use encodec for PosteriorEncoder+Decoder?

  #17 opened a year ago by fkwlqm
  2

• how do i use train for single voice

  #15 opened 2 years ago by wac81
  3

• question about demo wavs

  #16 opened a year ago by TinaChen95
  1

• change the sampling rate

  #12 opened 2 years ago by isletennos
  1

• 44100Hz and Ja Support

  #13 opened 2 years ago by tonnetonne814
  1

• Questions about "3.3. Implementation Details."

  #10 opened 2 years ago by isletennos
  4

• Question about vq in the paper

  #11 opened 2 years ago by taalua
  1

• No Arg Named axis for torch.cat

  #8 opened 2 years ago by Aloento
  6

• What is the role of "tone" in the return value of "text_to_sequence"?

  #9 opened 2 years ago by isletennos
  2

• Question, how do I launch app.py?

  #6 opened 2 years ago by GUUser91
  9

• about training PITS at 44100hz sampling rate

  #7 opened 2 years ago by innnky
  2

• Release Date?

  #1 opened 2 years ago by WhiteFu
  5

• Training Code

  #4 opened 2 years ago by hdmjdp
  1

• Multi-language support?

  #3 opened 2 years ago by Chopin68
  2

• Is there any sample for voice conversion?

  #2 opened 2 years ago by choiHkk
  2