wav2letter++: The Fastest Open-source Speech Recognition System
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.
Code (8)
Tasks
Speech RecognitionSimilar Papers 제목 키워드 기반
CIEMPIESS: A New Open-Sourced Mexican Spanish Radio Corpus
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 ModellingLetter-Based Speech Recognition with Gated ConvNets
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+1Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
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 RecognitionOpen Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti
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 ReductionApplying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages
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