Sorry, you need to enable JavaScript to visit this website.

wav2letter++ : A Fast Open-Source Speech Recognition Framework

Citation Author(s):
Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert
Submitted by:
Vineel Pratap
Last updated:
13 May 2019 - 8:40am
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
Vineel Pratap
Paper Code:
4733

Abstract 

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. 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.

up
0 users have voted:

Dataset Files

wav2letter++-poster.pdf

(1323)