Rongjiehuang/FastDiff

Issues

• Pretrained model is lost

  #27 opened 6 months ago by cantabile-kwok
  2

• Pretrain models is lost

  #28 opened 6 months ago by isjwdu
  1

• train problem

  #26 opened 2 years ago by yyh565655555
  0

• process problem

  #25 opened 2 years ago by yyh565655555
  0

• Loss nan occurred in the fastdiff training time

  #24 opened 2 years ago by GY123123
  0

• pretrain model

  #23 opened 2 years ago by yyh565655555
  1

• Training config sample rate 24Khz

  #22 opened 2 years ago by BuaaAlban
  0

• question for hyper-parameters N

  #21 opened 2 years ago by zy511361103
  0

• Got 404 not found when visiting ProDiff

  #20 opened 2 years ago by yqzhishen
  0

• Integrating with tacotron 1

  #19 opened 2 years ago by the6thsense
  3

• Noisy outputs when running LJSpeech checkpoint on Tacotron mel spectrograms

  #4 opened 3 years ago by patrickvonplaten
  10

• About audio sample rate and other hparams

  #18 opened 2 years ago by yqzhishen
  1

• No module named 'modules.tts

  #16 opened 2 years ago by yijingshihenxiule
  1

• Will FastDiff work well with singing voice synthesis?

  #17 opened 2 years ago by yqzhishen
  1

• cannot import name 'waveglow' from 'vocoders'

  #15 opened 2 years ago by payymann
  1

• demo_tts.py missing packages & run.py KeyError

  #14 opened 2 years ago by ahmedlila
  1

• ModuleNotFoundError: No module named 'utils.rnnoise'

  #13 opened 2 years ago by 15755841658
  1

• No module named 'utils'

  #12 opened 2 years ago by Patchethium
  2

• Finetune on my owndataset

  #7 opened 3 years ago by abdelrahmanhassan12
  6

• issue with demo yaml file

  #11 opened 2 years ago by mattolson93
  1

• Pre-defined noise schedule

  #9 opened 2 years ago by yahshibu
  2

• Question about noise scheduling process.

  #8 opened 2 years ago by LEECHOONGHO
  1

• Optimizer parameters

  #10 opened 2 years ago by yahshibu
  1

• Question about FastDiff-TTS

  #3 opened 2 years ago by LEECHOONGHO
  3

• How about fastdiff's support for Chinese voice?

  #6 opened 3 years ago by Wulx2050
  1

• Release of fine-tuned FastSpeech2 model

  #5 opened 3 years ago by patrickvonplaten
  1

• Is utils/ddp_utils.py missing?

  #2 opened 3 years ago by drscotthawley
  2