Add model card

This PR adds a model card by linking it to the paper [Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://huggingface.co/papers/2412.15322).

It also adds relevant metadata such as the pipeline tag, library name, and license.

README.md

@@ -1,8 +1,9 @@
 ---
 license: mit
-language:
-- en
+library_name: diffusers
+pipeline_tag: text-to-audio
 ---
-Code: https://github.com/hkchengrex/MMAudio
-license: mit
----
+
+This repository contains the model of the paper [Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://huggingface.co/papers/2412.15322).
+
+Code: https://github.com/hkchengrex/MMAudio