Espresso: A Fast End-to-end Neural Speech Recognition Toolkit

Authors:
  • YWYiming Wang
    Yiming Wang
  • TCTongfei Chen
    Tongfei Chen
  • HXHainan Xu
    Hainan Xu
  • SDShuoyang Ding
    Shuoyang Ding
  • HLHang Lv
    Hang Lv
  • YSYiwen Shao
    Yiwen Shao
  • NPNanyun Peng
    Nanyun Peng
  • LXLei Xie
    Lei Xie
  • SWShinji Watanabe
    Shinji Watanabe
  • SKSanjeev Khudanpur
    Sanjeev Khudanpur

Abstract
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).