richieyoum/voice_cloning

Issues

• t-sne visualization of embedding output

  #14 opened 3 years ago by richieyoum
  0

• add function for single audio inferencing on speaker embedding

  #19 opened 3 years ago by richieyoum
  0

• add validation scoring function

  #18 opened 3 years ago by richieyoum
  0

• train a baseline speaker embedding model

  #13 opened 3 years ago by richieyoum
  0

• concatenate speaker embedding output to text embedding output

  #16 opened 3 years ago by richieyoum
  0

• investigate dataloader modification required for adding speaker embedding output

  #15 opened 3 years ago by richieyoum
  0

• simple classifier of speakers based on speaker embedding

  #17 opened 3 years ago by richieyoum
  0

• implement similarity matrix

  #4 opened 3 years ago by pieceOpiland
  0

• graident scaling & clipping

  #6 opened 3 years ago by pieceOpiland
  0

• *** implement train function

  #7 opened 3 years ago by richieyoum
  0

• implement dataset class and dataloader class

  #2 opened 3 years ago by richieyoum
  0

• implement loss function

  #5 opened 3 years ago by pieceOpiland
  0

• implement forward function

  #3 opened 3 years ago by pieceOpiland
  0

• Create stub file

  #1 opened 3 years ago by richieyoum
  2