Improve model card for `espnet/aceopencpop_svs_visinger2_40singer_pretrain`

README.md

@@ -1,14 +1,24 @@
 ---
+datasets:
+- acesinger
+language: zh
+license: cc-by-4.0
 tags:
 - espnet
 - audio
 - singing-voice-synthesis
-language: zh
-datasets:
-- acesinger
-license: cc-by-4.0
+pipeline_tag: text-to-audio
+library_name: espnet
 ---
 
+# SingingSDS: A Singing-Capable Spoken Dialogue System for Conversational Roleplay Applications
+
+This repository contains the `espnet/aceopencpop_svs_visinger2_40singer_pretrain` model, an ESPnet2 Singing Voice Synthesis (SVS) component used within the broader [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 for Conversational Roleplay Applications](https://huggingface.co/papers/2511.20972)
+*   **Code (SingingSDS GitHub)**: https://github.com/SingingSDS/SingingSDS
+*   **Demo (Hugging Face Space)**: https://huggingface.co/spaces/espnet/SingingSDS
+
 ## ESPnet2 SVS model
 
 ### `espnet/aceopencpop_svs_visinger2_40singer_pretrain`
@@ -28,8 +38,6 @@ cd egs2/acesinger/svs1
 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/aceopencpop_svs_visinger2_40singer_pretrain
 ```
 
-
-
 ## SVS config
 
 <details><summary>expand</summary>
@@ -514,8 +522,6 @@ distributed: false
 
 </details>
 
-
-
 ### Citing ESPnet
 
 ```BibTex
@@ -555,4 +561,4 @@ or arXiv:
   archivePrefix={arXiv},
   primaryClass={cs.CL}
 }
-```
+```