Improve model card: Add pipeline tag, license, paper, code and demo links (#1)

- Improve model card: Add pipeline tag, license, paper, code and demo links (2567f762b5af6a326872590850475cc06cbbee90)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,28 @@
 ---
-tags:
-- espnet
-- audio
-- singing-voice-synthesis
 language:
 - zh
 - ja
 library_name: espnet
+tags:
+- espnet
+- audio
+- singing-voice-synthesis
+pipeline_tag: text-to-audio
+license: mit
 ---
+
+# espnet/visinger2-zh-jp-multisinger-svs: Singing Voice Synthesis Model for SingingSDS
+
+This model is `espnet/visinger2-zh-jp-multisinger-svs`, a multilingual (Chinese and Japanese) singing voice synthesis (SVS) component. It is a key part of the [SingingSDS: A Singing-Capable Spoken Dialogue System for Conversational Roleplay Applications](https://huggingface.co/papers/2511.20972) project.
+
+- 📚 [Paper: SingingSDS: A Singing-Capable Spoken Dialogue System](https://huggingface.co/papers/2511.20972)
+- 💻 [Project Code on GitHub: SingingSDS](https://github.com/SingingSDS/SingingSDS)
+- 🚀 [Live Demo on Hugging Face Spaces](https://huggingface.co/spaces/espnet/SingingSDS)
+
+<div align="center">
+  <img src="https://github.com/SingingSDS/SingingSDS/raw/main/assets/demo.png" alt="SingingSDS Interface" style="max-width: 100%; height: auto;"/>
+</div>
+
 ## ⚠️ Notice
 
 **This model is for research use only and is strictly prohibited for any commercial use.**  
@@ -596,4 +611,4 @@ booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia}
   doi={10.21437/Interspeech.2018-1456},
   url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
 }
-```
+```