wav2letter++: The Fastest Open-source Speech Recognition System
Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/facebookresearch/wav2letternone★ 6,445
- github.com/jakeju/wav2letternone★ 0
- github.com/flashlight/wav2letternone★ 0
- github.com/krantirk/Wav2letterPlusnone★ 0
- github.com/lilei-John/wav2letternone★ 0
- github.com/gcambara/wav2letternone★ 0
- github.com/mailong25/wav2letternone★ 0
- github.com/bsridatta/wav2letter-Swedishnone★ 0
Abstract
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.