We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. ESPnet-ST is a new project inside end-to-end speech processing toolkit, ESPnet, which integrates or newly implements automatic speech recognition, machine translation, and text-to-speech functions for speech translation. We provide all-in-one recipes including data pre-processing, feature extraction, training, and decoding pipelines for a wide range of benchmark datasets. Our reproducible results can match or even outperform the current state-of-the-art performances; these pre-trained models are downloadable. The toolkit is publicly available at https://github.com/espnet/espnet.
@article{arxiv.2004.10234,
title = {ESPnet-ST: All-in-One Speech Translation Toolkit},
author = {Hirofumi Inaguma and Shun Kiyono and Kevin Duh and Shigeki Karita and Nelson Enrique Yalta Soplin and Tomoki Hayashi and Shinji Watanabe},
journal= {arXiv preprint arXiv:2004.10234},
year = {2020}
}
Comments
Accepted at ACL 2020 System Demonstration (update Table1, fix typo)