bshall/knn-vc

Issues

• Using knn-vc for audio streams

  #39 opened a month ago by vitreo12
  0

• Cannot download model.

  #42 opened a month ago by sai4july
  5

• Using a Generator Network Before the Vocoder

  #41 opened 2 months ago by saeedzou
  1

• onnx support

  #40 opened 2 months ago by zdj97
  0

• Conversion output has very strong similarity to source audio.

  #18 opened a year ago by Sassun
  4

• Using better neural vocoder GAN (BIGVGAN, RVQGAN ...)

  #38 opened 3 months ago by tcourat
  1

• Request

  #36 opened 4 months ago by dillfrescott
  2

• Question about the Used Hardware

  #37 opened 4 months ago by CCMaure
  1

• extend to other SSL model features

  #22 opened 5 months ago
  0

• How to plug-in new finetuned HiFiGAN?

  #34 opened 5 months ago by youssefabdelm
  1

• Some question about features KNN

  #35 opened 7 months ago by huutuongtu
  2

• Will this work with 44100hz audio?

  #23 opened a year ago by dillfrescott
  4

• loss issues encountered in fine-tuning the model

  #26 opened a year ago by wangtao201919
  6

• Some questions about implementation

  #31 opened 10 months ago by TOGA101
  2

• Hints on improvements for training and matching

  #33 opened 10 months ago by asusdisciple
  3

• Matching pool empty

  #32 opened a year ago by asusdisciple
  2

• Using another batch size in training

  #30 opened a year ago by asusdisciple
  2

• Maybe mention memory consumption in readme.md?

  #29 opened a year ago by asusdisciple
  3

• Will this work for singing voice conversion (svc)?

  #28 opened a year ago by billnye2
  2

• Size mismatch error

  #25 opened a year ago by JBloodless
  2

• Error in quickstart

  #24 opened a year ago by lesept777
  2

• Training HiFiGAN on higher quality data

  #11 opened a year ago by gaurangbharti1
  16

• Considering context around source features

  #19 opened a year ago by wilson97
  2

• Choice for k

  #17 opened a year ago by tebin
  2

• prematch_dataset run very slow

  #15 opened a year ago by fangg2000
  4

• prematch argument

  #16 opened a year ago by d2sys
  2

• Torch Hub CPU inference support

  #14 opened a year ago by skyler14
  1

• Question about WavLM layer choice

  #13 opened a year ago by space-pope
  2

• out_wav is a wav file?

  #12 opened a year ago by fangg2000
  1

• Output is a bit shaky, how to fix that?

  #9 opened a year ago by Souvic
  1

• WavLM Base+ over Large?

  #10 opened a year ago by Pathos0925
  1

• SoX effect fails on Windows with SoundFile backend

  #5 opened a year ago by Zuellni
  1

• Discriminator checkpoint

  #8 opened a year ago by hippotabek
  1

• An error when loading models

  #6 opened a year ago by chienlinhuang1116
  2

• torchaudio version

  #7 opened a year ago by Blakey-Gavin
  2

• bigvgan as vocoder

  #3 opened a year ago by eschmidbauer
  1

• Link to paper

  #1 opened a year ago by Ashraf-Ali-aa
  0

• An error when check input type

  #2 opened a year ago by yzmyyff
  0