This PR improves the model card by:
- Updating the `pipeline_tag` to `audio-to-audio` to better reflect the vocoder's function.
- Adding a link to the research paper: [Joycent: Diffusion-based Accent TTS without Accented Phone Prediction](https://huggingface.co/papers/2606.16417).
- Updating the link to the official GitHub repository.
- Adding the BibTeX citation for researchers.