Giters
mpc001
/
auto_avsr
Auto-AVSR: Lip-Reading Sentences Project
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
158
Watchers:
5
Issues:
35
Forks:
41
mpc001/auto_avsr Issues
Error when training on LRS2
Updated
2 months ago
Whether do you perform deduplication between the LRS3 test set and AVSpeech
Updated
3 months ago
Problem about training
Updated
4 months ago
Problems with data processing using a self-built dataset
Updated
4 months ago
Comments count
1
train issue
Updated
4 months ago
Question about training on a Chinese dataset created by myself.
Closed
4 months ago
Running Demo gets ModuleNotFoundError: No module named 'six'
Updated
5 months ago
Comments count
5
test issue
Updated
5 months ago
Want to train VSR model for digit recognition using grid dataset.
Updated
5 months ago
Running demo.py in colab results in
Closed
a year ago
Comments count
7
What result should be obtained under normal circumstances after preprocessing?
Closed
6 months ago
Comments count
6
Asking for how to build the corpus for LRS2
Closed
6 months ago
Comments count
1
AVSpeech Dataset
Updated
7 months ago
Hydra Conflict Problem
Updated
7 months ago
Comments count
6
cannot import name 'eval_env' from 'torchaudio._internal.module_utils'
Updated
8 months ago
Comments count
1
Re-implementation error
Updated
8 months ago
Comments count
1
`cut_or_pad` function is wrong
Closed
9 months ago
Comments count
4
VSR Model Training Issues
Updated
9 months ago
Comments count
1
The AV-ASR pretrained models.
Closed
9 months ago
Comments count
1
About the real-time AVSR model
Closed
9 months ago
Comments count
1
A potential bug
Closed
9 months ago
Comments count
1
No module named 'ibug.face_alignment'
Closed
10 months ago
Comments count
1
Number of gpus / total batch size to reproduce the results in the paper
Closed
10 months ago
Comments count
1
The Audiovisual pretrained model.
Closed
a year ago
Number of GPUs for training
Closed
a year ago
Comments count
1
How to get audio from mp4 using torchaudio
Closed
a year ago
Comments count
2
Issue with hydra - Error merging data/dataset=cstm Key 'defaults' not in 'FairseqConfig'
Updated
a year ago
Comments count
6
How to use AUTO-AVSR to train a Chinese AVSR model
Closed
a year ago
Comments count
1
How to train an auto-avsr model from scratch through curriculum learning
Closed
a year ago
Comments count
1
Something went wrong with hydra and omegaconf
Closed
a year ago
Comments count
5
can i know input time?
Closed
a year ago
Comments count
4
Unicode Decode Error when running the LRS2 data preparation
Closed
a year ago
Comments count
2