Improve model card metadata

This PR improves the model card by correcting the `pipeline_tag` to `audio-text-to-text` and adding the `library_name` to better categorize the model on the Hugging Face Hub. This ensures the model is discoverable through relevant searches and improves its metadata.

README.md

@@ -1,13 +1,15 @@
 ---
 license: gpl-3.0
-pipeline_tag: any-to-any
+library_name: transformers
+pipeline_tag: audio-text-to-text
 tags:
 - omni
 ---
+
 # Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
 
 [![arXiv](https://img.shields.io/badge/arXiv-2506.13642-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2506.13642)
-[![arXiv](https://img.shields.io/badge/GitHub-Stream--Omni-black.svg?logo=github)](https://github.com/ictnlp/Stream-Omni)
+[![GitHub](https://img.shields.io/badge/GitHub-Stream--Omni-black.svg?logo=github)](https://github.com/ictnlp/Stream-Omni)
 [![model](https://img.shields.io/badge/%F0%9F%A4%97%20Huggingface%20-stream--omni--8b-orange.svg)](https://huggingface.co/ICTNLP/stream-omni-8b)
 [![data](https://img.shields.io/badge/%F0%9F%93%91%20Datasets%20-InstructOmni-green.svg)](https://huggingface.co/datasets/ICTNLP/InstructOmni)
 [![Badge](https://hitscounter.dev/api/hit?url=https%3A%2F%2Fgithub.com%2Fictnlp%2FStream-Omni&label=Visitors&icon=graph-up&color=%23dc3545)](https://github.com/ictnlp/Stream-Omni)
@@ -33,4 +35,4 @@ Stream-Omni is an end-to-end language-vision-speech chatbot that simultaneously
 
 > [!NOTE]
 >
-> **Stream-Omni can produce intermediate textual results (ASR transcription and text response) during speech interaction, offering users a seamless "see-while-hear" experience.**
+> **Stream-Omni can produce intermediate textual results (ASR transcription and text response) during speech interaction, offering users a seamless "see-while-hear" experience.**