heatz123/naturalspeech

Issues

• Demo samples use ground-truth duration or predicted duration?

  #38 opened 5 months ago by wownaoh9
  1

• Flip module explain

  #37 opened 6 months ago by chnk58hoang
  0

• Train loss

  #36 opened 8 months ago by yijingshihenxiule
  0

• Get duration label

  #35 opened 8 months ago by NDNM1408
  0

• How many time cost ?

  #6 opened 2 years ago by yiwei0730
  5

• Bug in preprocessing_duration functions

  #34 opened 9 months ago by NDNM1408
  0

• where is inference file ??

  #33 opened 9 months ago by saichand018
  0

• Can I train with higher sampling rate

  #32 opened 9 months ago by NDNM1408
  0

• Can you share experience on tuning the multiplers c_kl_fwd and c_e2e

  #12 opened 2 years ago by feng-yufei
  3

• Duration file

  #28 opened 2 years ago by AvichalJain
  1

• Is it normal to have negative value for loss_kl_fwd

  #22 opened a year ago by yuxinyuan
  2

• Is there a problem that the dimensions of logs_p and logs_q are inconsistent?

  #30 opened a year ago by 16dian11
  0

• Error w stft: RuntimeError: stft requires the return_complex parameter be given for real inputs, and will further require that return_complex=True in a future PyTorch release.

  #29 opened 2 years ago by IanRDomingo
  0

• Why is the shape of the duration file 2n+1 instead of n?

  #16 opened 2 years ago by ozingmw
  2

• Error While running Train.py

  #27 opened 2 years ago by athenasaurav
  2

• IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

  #25 opened 2 years ago by athenasaurav
  2

• How the models perform against VITS?

  #26 opened 2 years ago by jupinter
  0

• Inference code

  #9 opened 2 years ago by Murats7
  6

• AssertionError

  #15 opened 2 years ago by tandongli192
  1

• Any sample code for inference?

  #24 opened 2 years ago by narasimha-123
  1

• TypeError: '<=' not supported between instances of 'str' and 'int'

  #23 opened 2 years ago by wen0320
  2

• About the time complexity of attach_memory_bank.py

  #17 opened 2 years ago by TinaChen95
  2

• Is the project dead?

  #21 opened 2 years ago by KyotoSunshine
  0

• Any pre-trained models?

  #20 opened 2 years ago by Shiro836
  0

• Russian dataset training

  #19 opened 2 years ago by zhuangqirong
  0

• Any plan of Reproducing mix-phoneme BERT ?

  #10 opened 2 years ago by TinaChen95
  3

• About streaming output

  #14 opened 2 years ago by kendo6666
  1

• Is there a specific release plan for the project?

  #1 opened 2 years ago by WhiteFu
  3

• Can I train Turkish dataset with Transfer Learning?

  #13 opened 2 years ago by yasntrk
  0

• about cuda of dtw

  #11 opened 2 years ago by hdmjdp
  3

• French support

  #7 opened 2 years ago by projetmbc
  1

• Quality comparison to the original implementation

  #5 opened 2 years ago by dreamflasher
  1

• preprocess_texts issue

  #4 opened 2 years ago by gaga820402
  1

• About sample quality

  #2 opened 2 years ago by rishikksh20
  1