kan-bayashi/PytorchWaveNetVocoder

Issues

• Development plan

  #67 opened 5 years ago by kan-bayashi
  1

• could not find wav folder

  #65 opened 5 years ago by james20141606
  1

• typo in ljspeech/sd/run.sh

  #56 opened 6 years ago by kablooie
  1

• RuntimeError: zero(s) are found in periodogram, use eps option to floor

  #40 opened 6 years ago by greaber
  1

• Integration with Merlin

  #52 opened 6 years ago by Mark-Leisten-ajalaco
  1

• ValueError: numpy.ufunc has the wrong size, try recompiling. Expected 192, got 216

  #49 opened 6 years ago by RoelVdP
  7

• paralle training

  #48 opened 6 years ago by yfliao
  1

• Some questions about the subjective evaluation (MOS chart)

  #38 opened 6 years ago by unilight
  1

• about speaker

  #44 opened 6 years ago by assyoucan
  2

• Failed building wheel for pyworld and dtw-c

  #50 opened 6 years ago by Mark-Leisten-ajalaco
  1

• Mirror for m-ailabs dataset

  #47 opened 6 years ago by beknazar
  1

• Is adaptation of wavenet vocoder possible?

  #43 opened 6 years ago by cdemir1919
  2

• Abnormal noise is occurred at the silence region

  #42 opened 6 years ago by mjhwang93
  0

• auxiliary input

  #39 opened 7 years ago by james-wynne-dev
  0

• Some questions

  #30 opened 7 years ago by julianzaidi
  12

• Update information

  #34 opened 7 years ago by kan-bayashi
  3

• Speech to Speech

  #22 opened 7 years ago by PetrochukM
  16

• How to generate speech from features with WORLD vocoder

  #29 opened 7 years ago by ghostcow
  4

• ModuleNotFoundError: No module named 'pysptk'

  #21 opened 7 years ago by yishaicohe
  1

• Potential bug in feature_extract.py

  #25 opened 7 years ago by julianzaidi
  3

• Possible bug?

  #23 opened 7 years ago by ghostcow
  2

• ValueError: operands could not be broadcast together with shapes

  #20 opened 7 years ago by PetrochukM
  2

• Trying to train on nancy corpus subset

  #19 opened 7 years ago by ghostcow
  1

• To do

  #7 opened 7 years ago by kan-bayashi
  0