slp-rl/aero

Issues

• artifacts at the verge between existing and extended frequency bands

  #23 opened a year ago by Cunfu-Zhuge
  6

• hello Sure, here's the translation: "Why is my VCTK dataset in FLAC format instead of WAV? Is there a link for this?" Would you like to add or modify anything else?

  #29 opened 5 months ago by ssfacker
  1

• Logic for determining number of examples is off if segment and stride numbers differ

  #28 opened 6 months ago by pokepress
  0

• Optimal configuration for 12khz - 48khz

  #5 opened 2 years ago by fmac2000
  4

• Musdb model

  #16 opened a year ago by hayduck
  4

• real-time

  #26 opened 9 months ago by josefhernandez
  1

• Suggestion: Allow bfloat16 use to improve speed/memory usage

  #25 opened 10 months ago by pokepress
  1

• Request for Source Code of Your Impressive Demo Page

  #22 opened a year ago by yxlu-0102
  1

• AssertionError in training

  #18 opened a year ago by yxlu-0102
  3

• Predict.py output is silence

  #14 opened a year ago by harshvardhan-truefan
  19

• soundfile.LibsndfileError: <unprintable LibsndfileError object> Error in train.py

  #21 opened a year ago by yalcincenik
  6

• How to successfully install sox in conda virtual environment?

  #20 opened a year ago by yalcincenik
  0

• Is it possible to reduce GPU memory usage during inference?

  #19 opened a year ago by tshmak
  0

• Many related small questions

  #17 opened a year ago by shenberg
  1

• Predict on CPU

  #15 opened a year ago by patriotyk
  5

• Output not good when using predict and provided checkpoints

  #13 opened a year ago by Gandhi-Sagar
  2

• Applying the model for bandwidth extension (not super-resolution)

  #6 opened a year ago by eloimoliner
  12

• Training metrics

  #7 opened a year ago by fmac2000
  5

• “assert len(self.hr_set) == len(self.lr_set)" error

  #10 opened a year ago by psp0001060
  4

• A Question about vocals

  #11 opened a year ago by francqz31
  1

• BEHMGAN Training parameters

  #12 opened a year ago by abreuwallace
  1

• Training logs

  #4 opened 2 years ago by lsw5835
  2

• Model Comparison

  #8 opened 2 years ago by psp0001060
  2

• RuntimeError: Given groups=1, weight of size [48, 2, 1, 1], expected input[1, 4, 256, 7501] to have 2 channels, but got 4 channels instead

  #3 opened 2 years ago by FurkanGozukara
  1

• How to use this to improve audio quality of existing recordings?

  #2 opened 2 years ago by FurkanGozukara
  3

• Restore old tape recordings

  #1 opened 2 years ago by hobodrifterdavid
  1