Add pipeline tag and update paper link

This PR improves the model card by:
1. Adding the `pipeline_tag: text-generation` to the YAML metadata to ensure the model is discoverable in the correct category on the Hub.
2. Updating the placeholder paper link to point to the [Text2Score research paper](https://huggingface.co/papers/2605.13431).
3. Maintaining the existing detailed instructions for installation, inference, and citation.

README.md

@@ -1,14 +1,15 @@
 ---
+datasets:
+- emotionwave-company/text2score
 language:
 - en
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - music
 - text-to-music
 - sheet-music
 - pytorch
-datasets:
-- emotionwave-company/text2score
 ---
 
 # Text2Score: Generating Sheet Music From Textual Prompts
@@ -16,9 +17,9 @@ datasets:
 [![GitHub Repo](https://img.shields.io/badge/GitHub-Codebase-blue)](https://github.com/keshavbhandari/text2score)
 [![Demo](https://img.shields.io/badge/Demo-Live-brightgreen)](https://keshavbhandari.github.io/portfolio/text2score)
 [![Dataset](https://img.shields.io/badge/Dataset-HuggingFace-yellow)](https://huggingface.co/datasets/emotionwave-company/text2score)
-[![Paper](https://img.shields.io/badge/Paper-Arxiv_TBD-red)](#)
+[![Paper](https://img.shields.io/badge/Paper-Arxiv-red)](https://huggingface.co/papers/2605.13431)
 
-This repository hosts the pre-trained model weights for **Text2Score**, a model designed to generate sheet music directly from text prompts. 
+This repository hosts the pre-trained model weights for **Text2Score**, a model designed to generate sheet music directly from text prompts. The model is described in the paper [Text2Score: Generating Sheet Music From Textual Prompts](https://huggingface.co/papers/2605.13431).
 
 **Note on Usage:** To use this model, you do not need to download these weights manually. The inference scripts in our primary GitHub repository are configured to automatically download this checkpoint the first time you run them.