---
library_name: parallel-wavegan
license: mit
pipeline_tag: audio-to-audio
tags:
- vocoder
- parallel-wavegan
- joycent
- mandarin
- 16khz
---

# Joycent ParallelWaveGAN Vocoder

This repository stores the ParallelWaveGAN vocoder used by Joycent Mandarin accent text-to-speech inference, as presented in the paper [Joycent: Diffusion-based Accent TTS without Accented Phone Prediction](https://huggingface.co/papers/2606.16417).

The model generates 16 kHz audio from 80-bin mel spectrograms. 

- **Official Code:** [oshindow/Joycent-code](https://github.com/oshindow/Joycent-code)
- **Project Page:** [Demos](https://anonymous-accent-tts.github.io/Joycent-demo/)

## Usage

Keep `checkpoint-50000steps.pkl` and `config.yml` in the same directory when loading the model with ParallelWaveGAN:

```python
import yaml
from parallel_wavegan.utils import load_model

with open("config.yml", encoding="utf-8") as file:
    config = yaml.load(file, Loader=yaml.Loader)

vocoder = load_model("checkpoint-50000steps.pkl", config)
vocoder.remove_weight_norm()
vocoder.eval()
```

The Joycent implementation and inference instructions are available in the [official repository](https://github.com/oshindow/Joycent-code).

## Citation

```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},
}
```