issues
search
pigeonai-org
/
ViDove
🐦ViDove: RAG-Augmented End-to-end Multimodal Translation Agent
GNU General Public License v3.0
93
stars
9
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
added qwen2 for extracting the number of speakers
#20
Taka499
opened
1 month ago
0
fix yt-dlp
#19
yichen14
opened
2 months ago
1
Update app.py
#18
Zongheng00
closed
2 months ago
1
Update task_config.yaml
#17
Zongheng00
closed
2 months ago
0
Update MTA.py
#16
Zongheng00
closed
2 months ago
0
Update translator.py
#15
Zongheng00
closed
2 months ago
0
Mutiagent
#14
Zongheng00
closed
2 months ago
0
switch launch ip from 0.0.0.0 to localhost
#13
mengzelyu
closed
8 months ago
0
Assistant implementation
#12
JiaenLiu
closed
7 months ago
0
New Module: audio segmentation module
#11
yichen14
opened
8 months ago
0
Add Korean
#10
yichen14
closed
9 months ago
1
Add whisper v3
#9
Chester-Lin-Qiming
closed
8 months ago
0
ASR Module: refactorization and add Whisper-V3 through huggingface
#8
yichen14
closed
8 months ago
0
Pre-process Module: a better algorithm for form whole sentence
#7
yichen14
opened
10 months ago
0
Translation Module: tune gpt model for domain adaptation
#6
yichen14
closed
7 months ago
5
Evaluation: run through and debug evaluation
#5
yichen14
opened
10 months ago
1
Language Support: add KR & test on different languages
#4
yichen14
opened
10 months ago
0
User Experience: windows installation guide & code examples via Jupyter Notebook
#3
yichen14
opened
10 months ago
1
Testing: more unit tests
#2
yichen14
opened
10 months ago
0
Debug: many many bugs
#1
yichen14
opened
10 months ago
0