mpc001/auto_avsr

Issues

• Issue with hydra - Error merging data/dataset=cstm Key 'defaults' not in 'FairseqConfig'

  #6 opened a year ago by aprzez
  7

• Whether do you perform deduplication between the LRS3 test set and AVSpeech

  #35 opened 5 months ago by xiabingquan
  1

• Finetuning Recommendation

  #39 opened 3 months ago by hanif-rt
  0

• What is the minimum gpu requirement

  #38 opened 3 months ago by souvikg544
  0

• Issues training VSR from scratch

  #37 opened 3 months ago by FGiuliari
  1

• How to get audio from mp4 using torchaudio

  #8 opened a year ago by zyjcsf
  2

• Error when training on LRS2

  #36 opened 5 months ago by wcycqjy
  0

• Problem about training

  #34 opened 6 months ago by white1-doggy
  0

• Problems with data processing using a self-built dataset

  #33 opened 6 months ago by YuQing2000
  1

• train issue

  #32 opened 6 months ago by YuQing2000
  0

• Question about training on a Chinese dataset created by myself.

  #31 opened 7 months ago by liu33333
  0

• Running Demo gets ModuleNotFoundError: No module named 'six'

  #16 opened a year ago by M1ndBlast
  5

• test issue

  #30 opened 7 months ago by zhiishuo
  0

• Want to train VSR model for digit recognition using grid dataset.

  #28 opened 8 months ago by Chhaya-Trootech
  0

• Running demo.py in colab results in

  #10 opened a year ago by nastia-lado
  7

• What result should be obtained under normal circumstances after preprocessing?

  #25 opened 9 months ago by Xuzhejia
  6

• Asking for how to build the corpus for LRS2

  #27 opened 9 months ago by wcycqjy
  1

• AVSpeech Dataset

  #26 opened 9 months ago by shadtorrie
  0

• Hydra Conflict Problem

  #7 opened a year ago by SarahSalimpour
  6

• cannot import name 'eval_env' from 'torchaudio._internal.module_utils'

  #24 opened a year ago by YuQing2000
  1

• Re-implementation error

  #23 opened a year ago by jeonhuhuhu
  1

• `cut_or_pad` function is wrong

  #20 opened a year ago by xiabingquan
  4

• VSR Model Training Issues

  #22 opened a year ago by jeonhuhuhu
  1

• The AV-ASR pretrained models.

  #14 opened a year ago by yinghuozijin
  1

• About the real-time AVSR model

  #19 opened a year ago by csf123123
  1

• A potential bug

  #18 opened a year ago by tomato18463
  1

• No module named 'ibug.face_alignment'

  #17 opened a year ago by mabaisen
  1

• Number of gpus / total batch size to reproduce the results in the paper

  #15 opened a year ago by tomato18463
  1

• The Audiovisual pretrained model.

  #13 opened a year ago by yinghuozijin
  0

• Number of GPUs for training

  #9 opened a year ago by naraysa
  1

• How to use AUTO-AVSR to train a Chinese AVSR model

  #4 opened a year ago by MiningIrving
  1

• How to train an auto-avsr model from scratch through curriculum learning

  #5 opened a year ago by sara-kkk
  1

• Something went wrong with hydra and omegaconf

  #3 opened a year ago by jinchiniao
  5

• can i know input time?

  #2 opened a year ago by saeu5407
  4

• Unicode Decode Error when running the LRS2 data preparation

  #1 opened a year ago by gak97
  2