NeurST: Neural Speech Translation Toolkit

Abstract

NeurST is an open-source toolkit for neural speech translation. The toolkit mainly focuses on end-to-end speech translation, which is easy to use, modify, and extend to advanced speech translation research and products. NeurST aims at facilitating the speech translation research for NLP researchers and building reliable benchmarks for this field. It provides step-by-step recipes for feature extraction, data preprocessing, distributed training, and evaluation. In this paper, we will introduce the framework design of NeurST and show experimental results for different benchmark datasets, which can be regarded as reliable baselines for future research. The toolkit is publicly available at https://github.com/bytedance/neurst/ and we will continuously update the performance of NeurST with other counterparts and studies at https://st-benchmark.github.io/.

arXiv commentAccepted by ACL 2021 (system demonstration)

References in corpus (7)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Mixed Precision Training
• Horovod: fast and easy distributed deep learning in TensorFlow
• Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
• fairseq S2T: Fast Speech-to-Text Modeling with fairseq
• End-to-End Speech Translation with Knowledge Distillation
• "Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation

Cited by in corpus (2)

• Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
• The Volctrans Neural Speech Translation System for IWSLT 2021