This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker variants. To enable training speech synthesis models with less curated data, a number of preprocessing tools are built and their importance is shown empirically. To facilitate faster iteration of development and analysis, a suite of automatic metrics is included. Apart from the features added specifically for this extension, fairseq S^2 also benefits from the scalability offered by fairseq and can be easily integrated with other state-of-the-art systems provided in this framework. The code, documentation, and pre-trained models are available at https://github.com/pytorch/fairseq/tree/master/examples/speech_synthesis.
@article{arxiv.2109.06912,
title = {fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit},
author = {Changhan Wang and Wei-Ning Hsu and Yossi Adi and Adam Polyak and Ann Lee and Peng-Jen Chen and Jiatao Gu and Juan Pino},
journal= {arXiv preprint arXiv:2109.06912},
year = {2021}
}