README.md

---
license: apache-2.0
language:
- en
library_name: transformers
---

# FastSpeech2Conformer HiFi-GAN Vocoder

This is the HiFi-GAN vocoder for use with the FastSpeech2Conformer text-to-speech and voice conversion models.

The FastSpeech2Conformer model was proposed with the paper [Recent Developments On Espnet Toolkit Boosted By Conformer](https://arxiv.org/abs/2010.13956) by Pengcheng Guo, Florian Boyer, Xuankai Chang, Tomoki Hayashi, Yosuke Higuchi, Hirofumi Inaguma, Naoyuki Kamo, Chenda Li, Daniel Garcia-Romero, Jiatong Shi, Jing Shi, Shinji Watanabe, Kun Wei, Wangyou Zhang, and Yuekai Zhang. It was first released [in this repository](https://github.com/espnet/espnet). The license used is [Apache 2.0](https://github.com/espnet/espnet/blob/master/LICENSE).

Disclaimer: The team releasing FastSpeech2Conformer did not write a model card for this model, so this was written by a Hugging Face contributor.