Rudrabha/Lip2Wav

Issues

• Pytorch implementation for lip2wav-multispeaker

  #46 opened 2 years ago by JGJY02
  0

• Training on LRS3 or custom data

  #44 opened 2 years ago by AvivSham
  0

• Help for the installation

  #43 opened 2 years ago by PeterPedro
  0

• Dataset Downloading Error

  #8 opened 5 years ago by AvivSham
  3

• Real time speech generation

  #42 opened 2 years ago by Quidos
  0

• How much time did it take for you guys to train your model?

  #41 opened 2 years ago by ashwath98
  0

• Results of training on my own dataset

  #39 opened 3 years ago by dongdongdashen
  5

• WER

  #38 opened 3 years ago by Domhnall-Liopa
  0

• during preprocess how to save frames without faces？

  #37 opened 3 years ago by dongdongdashen
  2

• Teacher forcing on TIMIT and GRID dataset

  #29 opened 4 years ago by hjzzju
  2

• Unable to reproduce the score claimed in paper

  #35 opened 3 years ago by psui3905
  0

• consistency of input frames length and output waveform length

  #34 opened 3 years ago by rita-zeng
  0

• Question about hyper parameters: 'mel_overlap'

  #33 opened 3 years ago by rita-zeng
  0

• how to run inference?

  #32 opened 4 years ago by crankyz
  1

• The pre-trained model does not seem to work well

  #21 opened 4 years ago by enhuiz
  10

• How to avoid “CUDA out of memory” in PyTorch

  #30 opened 4 years ago by Sagar1998
  2

• How many steps needed for multi-speaker model

  #31 opened 4 years ago by kavinvin
  0

• Can't resume training from checkpoint

  #27 opened 4 years ago by graham-eisele
  1

• Train/test split for GRID and TIMIT and WER measurement.

  #18 opened 4 years ago by enhuiz
  1

• how to generate voice from video?

  #20 opened 4 years ago by molo32
  2

• Error while training the model on any data

  #28 opened 4 years ago by noamkatz
  6

• Pre-processing and training not working on custom dataset?

  #25 opened 4 years ago by graham-eisele
  16

• about time cost

  #26 opened 4 years ago by MontaEllis
  1

• Questions about data preprocessing

  #24 opened 4 years ago by Kuray107
  4

• Difference between mel.npz and ref.npz

  #23 opened 4 years ago by joannahong
  1

• Training error with "ValueError: all input arrays must have the same shape"

  #16 opened 4 years ago by kavinvin
  4

• ModuleNotFoundError: No module named 'numpy

  #17 opened 4 years ago by bitcoinbrisbane
  0

• training and test split for GRID and TCD-TIMIT

  #6 opened 5 years ago by WillQuCD
  2

• Is this model on google colab?

  #15 opened 4 years ago by Kreijstal
  1

• Encountered ValueError during training

  #14 opened 4 years ago by rita-zeng
  4

• Bug in multispeaker branch

  #13 opened 4 years ago by miraodasilva
  1

• When you can't detect a face

  #10 opened 5 years ago by MontaEllis
  2

• Dataset preprocessing

  #12 opened 5 years ago by naba89
  1

• Great project!

  #11 opened 5 years ago by sberryman
  4

• About teacher force

  #7 opened 5 years ago by MontaEllis
  1

• About SV2TTS concat

  #5 opened 5 years ago by MontaEllis
  1

• How Can I Get Generated Text?

  #4 opened 5 years ago by erkankaracakan
  1

• Lip2Wav dataset not available

  #2 opened 5 years ago by tomguluson92
  2

• Do you consider to use new Speech synthesis model ?

  #3 opened 5 years ago by dathudeptrai
  1