video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions.
AI & ML interests
https://www.ee.tsinghua.edu.cn/en/
Recent Activity
Organization Card
Department of Electronic Engineering, Tsinghua University
models
13
tsinghua-ee/WAVE-7B
Updated
tsinghua-ee/video_SALMONN2plus_72B_audioAlign
Updated
ā¢
1
tsinghua-ee/video_SALMONN2plus_7B_audioAlign
9B
ā¢
Updated
ā¢
422
tsinghua-ee/SALMONN
Automatic Speech Recognition
ā¢
Updated
ā¢
49
tsinghua-ee/video-SALMONN-2_plus_72B
Updated
ā¢
86
ā¢
2
tsinghua-ee/video-SALMONN-2_plus_3B
Updated
ā¢
677
ā¢
2
tsinghua-ee/video-SALMONN-2_plus_7B
Updated
ā¢
686
ā¢
6
tsinghua-ee/video-SALMONN-2
Video-Text-to-Text
ā¢
9B
ā¢
Updated
ā¢
189
tsinghua-ee/Speech_Quality_Assessment
Updated
ā¢
1
tsinghua-ee/F-16
Video-Text-to-Text
ā¢
Updated
ā¢
27
datasets
7
tsinghua-ee/SACRED-Bench
Viewer
ā¢
Updated
ā¢
2.48k
ā¢
69
tsinghua-ee/F-16-NBA
Preview
ā¢
Updated
ā¢
42
tsinghua-ee/AVUTBenchmark
Viewer
ā¢
Updated
ā¢
3.28k
ā¢
4.78k
ā¢
1
tsinghua-ee/video-SALMONN_2_testset
Preview
ā¢
Updated
ā¢
166
tsinghua-ee/QualiSpeech
Viewer
ā¢
Updated
ā¢
14.6k
ā¢
603
ā¢
21
tsinghua-ee/RivaBench
Viewer
ā¢
Updated
ā¢
542
ā¢
546
ā¢
2
tsinghua-ee/SAVEBench
Preview
ā¢
Updated
ā¢
98
ā¢
3