wav2letter++: The Fastest Open-source Speech Recognition System
Facebook AI Research
arXiv:1812.07625 [cs.CL], 18 Dec 2018
@article{pratap2018wav,
title={wav2letter++: The Fastest Open-source Speech Recognition System},
author={Pratap, Vineel and Hannun, Awni and Xu, Qiantong and Cai, Jeff and Kahn, Jacob and Synnaeve, Gabriel and Liptchinsky, Vitaliy and Collobert, Ronan},
year={2018},
month={dec},
archivePrefix={"arXiv"},
primaryClass={cs.CL}
}
This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework. wav2letter++ is written entirely in C++, and uses the ArrayFire tensor library for maximum efficiency. Here we explain the architecture and design of the wav2letter++ system and compare it to other major open-source speech recognition systems. In some cases wav2letter++ is more than 2x faster than other optimized frameworks for training end-to-end neural networks for speech recognition. We also show that wav2letter++’s training times scale linearly to 64 GPUs, the highest we tested, for models with 100 million parameters. High-performance frameworks enable fast iteration, which is often a crucial factor in successful research and model tuning on new datasets and tasks.
December 23, 2018 by hgpu
