Wendison/VQMIVC

Issues

• Why speaker encoder can encode the information of speaker?

  #45 opened 6 months ago by liyihao17
  0

• problem have slove

  #44 opened 9 months ago by foolishcqx
  0

• Other vocoder

  #21 opened 3 years ago by 2Bye
  2

• Questions about the evaluation

  #42 opened a year ago by yjlolo
  2

• Question about different embeddings/representations

  #43 opened a year ago by arnabdas8901
  2

• voice conversion not happens after fine-tuned with pretrained model

  #38 opened 2 years ago by MuruganR96
  1

• Training for Indian Multi-Speaker/Multi-lingual VC

  #37 opened 2 years ago by MuruganR96
  1

• huggingface is broken

  #41 opened 2 years ago by OIiveTree
  1

• Traiining loss plunged

  #39 opened 2 years ago by yijingshihenxiule
  1

• Hugging Face App is broken

  #40 opened 2 years ago by davidalencia
  0

• What do z_dim and c_dim stand for？

  #36 opened 2 years ago by Hu-chengyang
  4

• lf0 question about convert phase

  #34 opened 2 years ago by powei-C
  3

• Training Loss Abnormal

  #35 opened 2 years ago by Haoyanlong
  3

• How to solve this problem?

  #33 opened 3 years ago by Hu-chengyang
  3

• How to solve this problem?

  #31 opened 3 years ago by Hu-chengyang
  2

• Mel stats and Vocoder

  #32 opened 3 years ago by winddori2002
  2

• what does gamma: 0.5 in config/training/cpc.ymal mean?

  #30 opened 3 years ago by Hu-chengyang
  3

• What is the "parallel-wavegan-decode" in cmd = ['parallel-wavegan-decode', '--checkpoint',...] ,it is a folder???

  #29 opened 3 years ago by DIO385
  2

• How to slove this problem?

  #27 opened 3 years ago by Hu-chengyang
  9

• In convert.py subprocess.call(['cp', src_wav_path, out_dir]) What does' CP 'mean?

  #28 opened 3 years ago by Hu-chengyang
  2

• NameError: name 'amp' is not defined . File "train.py", line 407, in train_model

  #23 opened 3 years ago by geni120
  3

• How can I calculate suitable parameters?

  #22 opened 3 years ago by ElizavetaSedova
  1

• about the model question

  #19 opened 3 years ago by Mike66666
  4

• How to calculate results

  #18 opened 3 years ago by sauravpd29
  3

• How to fine tune your model for another language dataset?

  #17 opened 3 years ago by shagho
  2

• Error: ValueError: Buffer has wrong number of dimensions (expected 1, got 2)

  #25 opened 3 years ago by dillfrescott
  2

• Docker deploy keeps saying {"message":"Could not convert file input input_source to Path"}

  #24 opened 3 years ago by dillfrescott
  0

• Where can I get the silence trimmed VCTK corpus?

  #20 opened 3 years ago by Aria-K-Alethia
  2

• Loss value and reconstruction gender change

  #15 opened 3 years ago by inconnu11
  1

• Loss is zero

  #16 opened 3 years ago by kikirizki
  2

• Can I use another language without re-training?

  #14 opened 3 years ago by kikirizki
  2

• Question About Batch Size, number of Epochs and Learning Rate

  #13 opened 3 years ago by jlmarrugom
  6

• "Buffer has wrong number of dimensions (expected 1, got 2)" error when running demo on Replicate

  #12 opened 3 years ago by AVTV64
  2

• Question About the Embedding

  #9 opened 3 years ago by jlmarrugom
  1

• Improper converted audio when source = reference

  #5 opened 3 years ago by vishalbhavani
  3

• The CPCLoss

  #7 opened 3 years ago by Liujingxiu23
  4

• checkpoint file not full

  #8 opened 3 years ago by manhlab
  1

• loglikeli and mi_est

  #6 opened 3 years ago by Liujingxiu23
  1

• Demo: the source in female-to-male does not sound right

  #4 opened 3 years ago by tonyswoo
  1

• The issue of vocoder in Inference progress

  #3 opened 4 years ago by TaoTaoFu
  14

• preprocess issue

  #1 opened 4 years ago by Chuk101
  8

• Pytorch version 1.3.1

  #2 opened 4 years ago by Chuk101
  1