issues
search
KAIST-AILab
/
SyncVSR
SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization (Interspeech 2024)
https://www.isca-archive.org/interspeech_2024/ahn24_interspeech.pdf
MIT License
14
stars
1
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Questions related to preprocess.py and the data augmentation methods
#16
davidingram123
opened
1 hour ago
4
the issue with the data.py
#15
davidingram123
closed
57 minutes ago
5
Request for Accuracy Graphs to Address Replication Issues
#14
davidingram123
closed
4 hours ago
4
How and Where Should the Audio-Token .plk File Be Used in the Inference Process?
#13
SUMIN080
opened
2 days ago
2
Issues related to installation and preprocessing of the Chinese dataset.
#12
daiyingjie2024
closed
6 days ago
4
model architecture related question
#11
daiyingjie2024
closed
6 days ago
1
Chinese dataset
#10
daiyingjie2024
closed
1 week ago
4
Can you provide me the pretrained of lrs. thanks in advance.
#9
Thaonguyennnee
closed
1 week ago
1
Can you provide the training code for CAS-VSR-W1k?
#8
wuhongsheng
closed
1 week ago
2
What kind of computing power is needed for training?
#7
wuhongsheng
closed
1 week ago
1
Train on custom dataset
#6
Thaonguyennnee
closed
1 week ago
4
can you test on [CMLR](https://www.vipazoo.cn/CMLR.html)
#5
wuhongsheng
closed
1 week ago
1
where is inference.py
#4
wuhongsheng
closed
1 week ago
0
Clarification on training sentence-level VSR
#3
EidanErlich
closed
2 weeks ago
3
Chinese support (or multi-langual)
#2
MonolithFoundation
closed
2 weeks ago
1
Checkpoint URL
#1
longkhanh-fam
closed
2 weeks ago
13