Update README.md

README.md

@@ -105,11 +105,11 @@ tags:
 # **CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages**
 [![Homepage](https://img.shields.io/badge/CLaMP%203%20Homepage-Coming%20Soon-lightgrey?style=for-the-badge&logo=home-assistant)](#)
 [![Paper](https://img.shields.io/badge/CLaMP%203%20Paper-Coming%20Soon-lightgrey?style=for-the-badge&logo=arxiv)](#)
-[![GitHub](https://img.shields.io/badge/Code-GitHub-181717?style=for-the-badge&logo=github)](https://github.com/sanderwood/clamp3)
-[![Demo](https://img.shields.io/badge/CLaMP%203%20Demo-Coming%20Soon-lightgrey?style=for-the-badge&logo=gradio)](#)
+[![GitHub](https://img.shields.io/badge/CLaMP%203%20Code-GitHub-181717?style=for-the-badge&logo=github)](https://github.com/sanderwood/clamp3)
+[![Demo](https://img.shields.io/badge/CLaMP%203%20Demo-Gradio-green?style=for-the-badge&logo=gradio)](https://huggingface.co/spaces/sanderwood/clamp3)
 [![Hugging Face](https://img.shields.io/badge/Model%20Weights-Hugging%20Face-ffcc00?style=for-the-badge&logo=huggingface)](https://huggingface.co/sander-wood/clamp3/tree/main)
-[![Dataset](https://img.shields.io/badge/M4--RAG%20Pretraining%20Dataset-Hugging%20Face-ffcc00?style=for-the-badge&logo=huggingface)](https://huggingface.co/datasets/sander-wood/m4-rag)
-[![Benchmark](https://img.shields.io/badge/WikiMT--X%20Evaluation%20Benchmark-Hugging%20Face-ffcc00?style=for-the-badge&logo=huggingface)](https://huggingface.co/datasets/sander-wood/wikimt-x)
+[![Dataset](https://img.shields.io/badge/M4--RAG%20Dataset-Hugging%20Face-ffcc00?style=for-the-badge&logo=huggingface)](https://huggingface.co/datasets/sander-wood/m4-rag)
+[![Benchmark](https://img.shields.io/badge/WikiMT--X%20Benchmark-Hugging%20Face-ffcc00?style=for-the-badge&logo=huggingface)](https://huggingface.co/datasets/sander-wood/wikimt-x)
 
 <p align="center">
   <img src="overview.png" alt="CLaMP 3 Overview" width="50%">
@@ -128,7 +128,7 @@ CLaMP 3 is a multimodal and multilingual framework for music information retriev
    - Trained on **27 languages** and generalizes to all **100 languages** supported by **[XLM-R](https://arxiv.org/abs/1911.02116)**.  
 
 - **Datasets & Benchmarking:**  
-   - **[M4-RAG](https://huggingface.co/datasets/sander-wood/m4-rag):** A **large-scale** dataset of **2.31M high-quality music-text pairs** across 27 languages and 194 countries.  
+   - **[M4-RAG](https://huggingface.co/datasets/sander-wood/m4-rag):** A **web-scale** dataset of **2.31M high-quality music-text pairs** across 27 languages and 194 countries.  
    - **[WikiMT-X](https://huggingface.co/datasets/sander-wood/wikimt-x):** A MIR benchmark containing **1,000 triplets** of sheet music, audio, and diverse text annotations.  
 
 ### **Applications**  
@@ -255,4 +255,4 @@ python inference_cls.py <weights_path> <feature_folder> <output_file>
 ```
 
 ## **Citation**
-*Coming Soon...*  
+*Coming Soon...*