---
license: apache-2.0
datasets:
- HuggingFaceFV/finevideo
- lmms-lab/LLaVA-Video-178K
- ShareGPT4Video/ShareGPT4Video
language:
- en
metrics:
- accuracy
base_model:
- Qwen/Qwen2-7B
- lmms-lab/llava-onevision-qwen2-7b-ov
- openai/whisper-large-v3
pipeline_tag: video-text-to-text
library_name: transformers
---

# video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models

Official model release of [video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models](https://github.com/bytedance/video-SALMONN-2)

[Github Link](https://github.com/bytedance/video-SALMONN-2)

[Paper Link](https://arxiv.org/abs/2506.15220)

## Results

<img width="857" height="510" alt="image" src="https://github.com/user-attachments/assets/aca20b2e-1e68-4b44-a26b-03d5f070b213" />