This PR enhances the model card for AVoCaDO by:
- Adding `pipeline_tag: video-text-to-text` to improve discoverability on the Hub, accurately reflecting the model's functionality of generating text descriptions from video input.
- Specifying `library_name: transformers` in the metadata, as evidence from `config.json` (`"transformers_version": "4.52.4"` and `Qwen2_5OmniForConditionalGeneration` architecture) confirms compatibility with the Hugging Face Transformers library, enabling an automated usage widget.
- Completing the `Citation` section with the appropriate BibTeX entry for the paper.
These updates provide more comprehensive information for users and integrate the model more effectively within the Hugging Face ecosystem.
# AVoCaDO: An <u>A</u>udio<u>V</u>isual Vide<u>o</u> <u>Ca</u>ptioner <u>D</u>riven by Temporal <u>O</u>rchestration
<p align="left">
<a href="https://avocado-captioner.github.io/"><img src="https://img.shields.io/badge/Project%20webpage-558b2f?style=for-the-badge"></a>
<a href="https://github.com/AVoCaDO-Captioner/AVoCaDO"><img src="https://img.shields.io/badge/Github-db8905?style=for-the-badge"></a>
<a href="https://arxiv.org/abs/todo"><img src="https://img.shields.io/badge/arXiv-red?style=for-the-badge"></a>
</p>
## ✨ Overview
Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding and generation. We introduce <b>AVoCaDO</b>, a powerful audiovisual video captioner driven by the temporal orchestration between audio and visual modalities. Experimental results demonstrate that AVoCaDO significantly outperforms existing open-source models across four audio…
