paper-with-me

홈 › Papers

wav2letter++: The Fastest Open-source Speech Recognition System

2018-12-18 · Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert

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.

📄 PDF Abstract BibTeX arXiv:1812.07625

Code (8)

bsridatta/wav2letter-Swedish
facebookresearch/wav2letter
flashlight/wav2letter
gcambara/wav2letter
jakeju/wav2letter
krantirk/Wav2letterPlus
lilei-John/wav2letter
mailong25/wav2letter

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus

2014-05-01 · LREC 2014 5 · Carlos Daniel Hern Mena, ez, Abel Herrera Camacho

Corpus de Investigaci{\'o}n en Espa{\~n}ol de M{\'e}xico del Posgrado de Ingenier{\'\i}a El{\'e}ctrica y Servicio Social{''} (CIEMPIESS) is a new open-sourced corpus extracted from Spanish spoken FM podcasts in the diale…

Language Modelling

Letter-Based Speech Recognition with Gated ConvNets

2017-12-22 · Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert

In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such …

DecoderLanguage ModelingLanguage Modellingspeech-recognition+1

Wav2Letter: an End-to-End ConvNet-based Speech Recognition System

2016-09-11 · arXiv 2016 9 · Ronan Collobert, Christian Puhrsch, Gabriel Synnaeve

This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the nee…

Speech Recognition

Open Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti

2018-08-31 · Nikita Gordienko, Peng Gang, Yuri Gordienko, Wei Zeng 외

Machine learning techniques are presented for automatic recognition of the historical letters (XI-XVIII centuries) carved on the stoned walls of St.Sophia cathedral in Kyiv (Ukraine). A new image dataset of these carved …

BIG-bench Machine LearningData AugmentationDimensionality Reduction

Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages

2020-12-22 · Cheng Yi, Jianzhong Wang, Ning Cheng, Shiyu Zhou 외

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be eff…

speech-recognitionSpeech Recognition