Wav2Letter++: A Fast Open-source Speech Recognition System
Vineel Pratap, Awni Y. Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert
Abstract
This paper introduces wav2letter++, a fast open-source deep learning speech recognition framework. wav2letter++ is written entirely in C++, and uses the ArrayFire tensor library for maximum efficiency. 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 2× faster than other optimized frameworks for training end-to-end neural networks for speech recognition. We also show that wav2letter++ training times scale linearly to 64 GPUs, the most 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.
BibTeX
@inproceedings{icassp2019_wav2letterafasto,
title = {Wav2Letter++: A Fast Open-source Speech Recognition System},
author = {Vineel Pratap and Awni Y. Hannun and Qiantong Xu and Jeff Cai and Jacob Kahn and Gabriel Synnaeve and Vitaliy Liptchinsky and Ronan Collobert},
booktitle = {ICASSP 2019},
year = {2019}
}