auspicious3000/SpeechSplit

Issues

• 其他数据集

  #74 opened 2 years ago by IndowK
  6

• Using encoder as speaker embedding extractor 关于使用编码器作为说话人嵌入提取器

  #79 opened a year ago by ehsienmu
  4

• 关于demo.ipynb的一些问题

  #77 opened a year ago by IndowK
  5

• 关于训练效果

  #78 opened a year ago by p1an-lin-jung
  1

• 关于编码器的问题

  #76 opened 2 years ago by IndowK
  2

• 音色迁移的问题

  #75 opened 2 years ago by IndowK
  4

• Cuda error

  #73 opened 2 years ago by popkingcorn
  1

• The validation loss is rising

  #54 opened 3 years ago by 3139725181
  10

• How to build the validation data?

  #62 opened 3 years ago by AShoydokova
  4

• The program has an error message: ValueError: high <= 0

  #72 opened 2 years ago by SeptemberN
  2

• Question: how many speakers was trained in pre-trained model?

  #42 opened 2 years ago by Kurei-Fujiwara
  1

• checkpoint_step001000000_ema.pth is missing

  #71 opened 2 years ago by Ludusss
  1

• why apply filter on the wav and why choose different min max for f0 for different gender

  #52 opened 2 years ago by WilliamZhaoz
  0

• Could you show me the codes about how to draw the pitch contours picture?

  #68 opened 2 years ago by sanena
  0

• Is it very slow for the Wavenet vocoder to synthesize a voice

  #69 opened 2 years ago by hhhuazi
  5

• What `demo.pkl` consists of ?

  #35 opened 4 years ago by CYT823
  3

• Question about padding

  #67 opened 3 years ago by summersunshine1
  3

• How to synthesis a speech which I need?

  #63 opened 3 years ago by sanena
  1

• Array error

  #64 opened 3 years ago by dillfrescott
  1

• make_metadata.py logic puzzle

  #34 opened 4 years ago by leijue222
  7

• Can it transfer RFU between different utterances?

  #44 opened 4 years ago by flagman
  1

• Does it will work on unseen data also? will it be able to convert voice of unseen speaker with different content than that of data in training, will we obtain the disentanglement?

  #27 opened 4 years ago by pycodebook
  8

• Training for encoder (i.e. embedding) usage only?

  #60 opened 3 years ago by tobwei
  1

• Only works for speakers in the training dataset?

  #61 opened 3 years ago by zhouyong64
  0

• about Downsample Factor

  #59 opened 3 years ago by yangdongchao
  1

• Obout downsampling implementation.

  #58 opened 3 years ago by yangdongchao
  1

• Content encoder definition

  #57 opened 3 years ago by pyrito
  2

• Could you please describe details of rhythm-only conversion ?

  #56 opened 3 years ago by dbkest
  1

• How to align multiple sequences while they are from different source?

  #43 opened 4 years ago by inconnu11
  2

• How to get a generated speech from the output of the trained Generator?

  #55 opened 3 years ago by 6lyx
  3

• F0 Converter for P - loss function values

  #36 opened 4 years ago by rishabhjain16
  7

• How to retrain the G model?

  #53 opened 3 years ago by 3139725181
  0

• How to fix the vibrato result?

  #46 opened 3 years ago by CYT823
  2

• mel spectrogram normalization range

  #51 opened 3 years ago by inconnu11
  1

• No module named 'synthesis'

  #37 opened 3 years ago by Merlin-721
  3

• Training bottleneck hparams

  #49 opened 3 years ago by Merlin-721
  1

• How to check speaker disentanglement during training?

  #50 opened 3 years ago by lambda-delta34
  1

• Training G and P at different sample rates

  #48 opened 3 years ago by Merlin-721
  3

• Learning rate for P (F0_Converter)

  #47 opened 3 years ago by Merlin-721
  2

• Using ParallelWaveGan instead of Wavenet

  #41 opened 3 years ago by vishal16babu
  4

• AttributeError: 'HParams' object has no attribute 'builder'

  #32 opened 4 years ago by LordBeardsteak
  6

• Question: Using a pretrained encoder for getting the speaker embedding.

  #29 opened 4 years ago by nischal-sanil
  3

• How to train your own model and apply it? I have come so far but having problem at solver.py

  #28 opened 4 years ago by FurkanGozukara
  8

• Tuning bottlenecks according to Appendix B.4

  #40 opened 4 years ago by vishal16babu
  2

• Downsampling for VCTK corpus

  #38 opened 4 years ago by biggytruck
  1

• Question: how much data was trained in pre-trained model?

  #33 opened 4 years ago by CYT823
  0

• How to split "Accent" information of the speaker?

  #30 opened 4 years ago by rppravin
  3

• RuntimeError: Error(s) in loading state_dict for WaveNet

  #26 opened 4 years ago by vlad-i
  3

• Can you solve the inference problem of audio not in the data set?

  #25 opened 4 years ago by c1a1o1
  0

• bug issue

  #24 opened 4 years ago by N1r
  1