Add pipeline tag and link to paper

README.md

@@ -1,5 +1,9 @@
 ---
-license: mit
+base_model:
+- spellbrush/AliasingFreeNeuralAudioSynthesis
+datasets:
+- sarulab-speech/mls_sidon
+- mythicinfinity/Libriheavy-HQ
 language:
 - en
 - ja
@@ -10,23 +14,20 @@ language:
 - pl
 - pt
 - es
+license: mit
+pipeline_tag: audio-to-audio
 tags:
 - speech
 - audio
 - vocoder
-datasets:
-- sarulab-speech/mls_sidon
-- mythicinfinity/Libriheavy-HQ
-base_model:
-- spellbrush/AliasingFreeNeuralAudioSynthesis
 ---
 
 # MioVocoder: High-Resolution Aliasing-Free Neural Vocoder for High-Fidelity Speech Generation
 
-
 [![GitHub](https://img.shields.io/badge/Code-GitHub-black)](https://github.com/Aratako/MioCodec)
+[![arXiv](https://img.shields.io/badge/arXiv-2512.20211-b31b1b.svg)](https://huggingface.co/papers/2512.20211)
 
-**MioVocoder** is a high-resolution, aliasing-free neural vocoder designed for high-fidelity speech generation. It is a fine-tuned version of the **Pupu-Vocoder (Small)** from the [Aliasing-Free Neural Audio Synthesis](https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis) (AFGen) project.
+**MioVocoder** is a high-resolution, aliasing-free neural vocoder designed for high-fidelity speech generation. It is a fine-tuned version of the **Pupu-Vocoder (Small)** from the paper [Aliasing-Free Neural Audio Synthesis](https://huggingface.co/papers/2512.20211) (AFGen).
 
 ## 🌟 Overview
 
@@ -90,6 +91,7 @@ vocoder = load_vocoder(
 ## 📜 Acknowledgements
 
 * **Original Architecture & Paper:** [Aliasing-Free Neural Audio Synthesis](https://arxiv.org/abs/2512.20211) (AFGen).
+* **Official Code:** [GitHub Repository](https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis)
 * **Base Weights:** Provided by the [Spellbrush](https://huggingface.co/spellbrush) team.
 
 ## 🖊️ Citation