Improve model card: add paper link, code link, and metadata

README.md

@@ -1,32 +1,50 @@
 ---
-license: mit
 library_name: pytorch
+license: mit
 pipeline_tag: text-to-speech
 tags:
-  - accent-tts
-  - mandarin
-  - joycent
-  - grad-tts
+- accent-tts
+- mandarin
+- joycent
+- grad-tts
 ---
 
-# Joycent Mandarin Accent TTS
+# Joycent: Diffusion-based Accent TTS without Accented Phone Prediction
+
+Joycent is a diffusion-based Mandarin accent text-to-speech (TTS) framework that synthesizes accented speech directly from standard phone sequences and speech references without requiring accented phone prediction. It integrates accent and speaker representations through conditional layer normalization (CLN) in the text encoder.
+
+- **Paper:** [Joycent: Diffusion-based Accent TTS without Accented Phone Prediction](https://huggingface.co/papers/2606.16417)
+- **Code:** [oshindow/Joycent-code](https://github.com/oshindow/Joycent-code)
+- **Demo:** [Joycent Demo Page](https://anonymous-accent-tts.github.io/Joycent-demo/)
 
-This repository stores the pretrained Joycent acoustic-model checkpoint for
-Mandarin accent text-to-speech synthesis.
+## Usage
 
-The model implementation and inference instructions are available in the
-[Joycent repository](https://github.com/anonymous-accent-tts/Joycent_demo).
+This repository stores the pretrained Joycent acoustic-model checkpoint (`grad_210.pt`). The model implementation and full inference instructions are available in the [official GitHub repository](https://github.com/oshindow/Joycent-code).
 
-Download the checkpoint with:
+You can download the checkpoint using the following snippet:
 
 ```python
 from huggingface_hub import hf_hub_download
 
 checkpoint_path = hf_hub_download(
-    repo_id="<namespace>/<model-name>",
+    repo_id="walston/joycent",
     filename="grad_210.pt",
 )
 ```
 
-Then pass the downloaded path to `joycent/inference_joycent.py` using
-`--acoustic-checkpoint`.
+Then, pass the downloaded path to `joycent/inference_joycent.py` using the `--acoustic-checkpoint` argument. Note that you will also need the [Joycent vocoder](https://huggingface.co/walston/joycent-vocoder) for full synthesis.
+
+## Citation
+
+If you find Joycent useful for your research, please cite:
+
+```bibtex
+@misc{wang2026joycentdiffusionbasedaccenttts,
+      title={Joycent: Diffusion-based Accent TTS without Accented Phone Prediction},
+      author={Xintong Wang and Ye Wang},
+      year={2026},
+      eprint={2606.16417},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+}
+```