Improve model card: add pipeline tag and project links

This PR improves the model card by adding the `audio-to-audio` pipeline tag to the metadata, which helps in model discovery. It also adds links to the paper, project page, and code repository for better documentation.

README.md

@@ -1,9 +1,10 @@
 ---
-license: mit
 language:
 - en
 - zh
 - ja
+license: mit
+pipeline_tag: audio-to-audio
 tags:
 - speech
 - singing
@@ -15,11 +16,11 @@ tags:
 - pytorch
 ---
 
-## Aliasing-Free Neural Audio Synthesis
+# Aliasing-Free Neural Audio Synthesis
 
 This is the official Hugging Face model repository for the paper **"[Aliasing-Free Neural Audio Synthesis](https://arxiv.org/abs/2512.20211)"**, which is the first work to achieve simple and efficient aliasing-free upsampling-based neural audio generation in the entire field of neural vocoders and codecs.
 
-For more details, please visit our [GitHub Repository](https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis).
+[**[Project Page]**](https://VocodexElysium.github.io/AliasingFreeNeuralAudioSynthesis/) [**[GitHub Repository]**](https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis) [**[Paper]**](https://arxiv.org/abs/2512.20211)
 
 ## Model Checkpoints
 
@@ -40,7 +41,7 @@ You need to put the pretrained models in:
   AliasingFreeNeuralAudioSynthesis/experiments
 ```
 
-of our official repository, and then follow the instructions written in the repository to resume, finetune, and inference our pretrained checkpoints.
+of our official repository, and then follow the instructions written in the [GitHub repository](https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis) to resume, finetune, and inference our pretrained checkpoints.
 
 ## Citation
 
@@ -51,4 +52,4 @@ of our official repository, and then follow the instructions written in the repo
   year         = {2025},
   journal      = {arXiv:2512.20211},
 }
-```
+```