lucidrains/voicebox-pytorch

Issues

• Training Example

  #25 opened a year ago by YKoustubhRao
  19

• Samples for audio and steps to run the experiment?

  #3 opened a year ago by RaiAmanRai
  3

• Default assignment of "cond".

  #51 opened 6 months ago by WECarol
  0

• Using WhisperSpeech Pre-trained Weights for TextToSemantic

  #49 opened 9 months ago by EomSooHwan
  0

• Mel model

  #44 opened a year ago by lixuyuan102
  10

• suggestion for symmetric alibi implementation.

  #10 opened a year ago by seastar105
  7

• Probably invalid infill logic

  #45 opened a year ago by ex3ndr
  0

• How to pick sigma?

  #46 opened 10 months ago by ex3ndr
  3

• Multi-Voice/Multi-Speaker?

  #31 opened a year ago by fakerybakery
  2

• Training Unconditional Model

  #43 opened a year ago by nrocketmann
  15

• Training TTS

  #42 opened a year ago by Subuday
  2

• speartts model

  #35 opened a year ago by happy-machine
  3

• Loss calculation

  #34 opened a year ago by YKoustubhRao
  1

• Deep network not converge

  #23 opened a year ago by lixuyuan102
  14

• VoiceBox Training

  #33 opened a year ago by yiwei0730
  3

• Pre-trained model weights

  #18 opened a year ago by Hades32
  3

• where to get the kmeans_path = './path/to/hubert/kmeans.bin file?

  #24 opened a year ago by furqan4545
  7

• Audio samples?

  #28 opened a year ago by blx0102
  2

• Dtype Issues on Inference

  #22 opened a year ago by nrocketmann
  0

• For reference

  #15 opened a year ago by chenht2021
  0

• dataloader

  #12 opened a year ago by yiwei0730
  0

• a mistake in rotary embbeding

  #13 opened a year ago by chenht2021
  1

• input dimension and model dimension can be different

  #7 opened a year ago by yzmyyff
  5

• There might be a bug in the loss calculation

  #6 opened a year ago by yzmyyff
  1

• The usage code throws exception

  #4 opened a year ago by yzmyyff
  1