wav2letter++ is a fast, open source speech processing toolkit from the Speech team at Facebook AI Research built to facilitate research in end-to-end models for speech recognition. It’s intended as a platform for rapid research in end-to-end speech recognition.
It follows a completely convolutional approach, and uses Convolutional Neural Networks (CNN) for acoustic modelling as well as language modelling.
wav2letter++ uses the ArrayFire tensor library and the flashlight machine learning library for maximum efficiency. ArrayFire is a highly optimized tensor library that can execute on multiple backends including a CUDA GPU back-end and a CPU backend. ArrayFire also uses just-in-time code generation to combine series of simple operations into a single kernel call. This results in faster execution for memory bandwidth bound operations and can reduce peak memory use.
wav2letter has been moved and consolidated into Flashlight in the ASR application.
wav2letter++ is free and open source software.
- Supports three main modes of training: train (flat-start training), continue (continuing with a checkpoint state), and fork (for e.g. transfer learning). The training pipeline scales seamlessly using data-parallel, synchronous stochastic-gradient-descent as well as inter process communications powered by NVIDIA Collective Communication Library. Training times scale linearly to 64 GPUs with 100 million parameters.
- Supports several end-to-end sequence models as well as a wide range of network architectures and activation functions.
- Supports feature extraction across different audio formats. The framework computes features on the fly prior to each network evaluation and enforces asynchrony and parallelization in order to maximize efficiency during the training of models.
- Training pipeline gives maximum flexibility for the user to experiment with different features, architectures and optimization parameters.
- Decoder is a beam-search decoder with several optimizations to improve efficiency.
- Written entirely in C++ which makes it efficient to train models and perform real-time decoding.
|New to Linux? Read our Linux for Starters series.|
|The largest compilation of the best free and open source software in the universe. Supplied with our legendary ratings charts.|
|Hundreds of in-depth reviews offering our unbiased and expert opinion on software.|
|Alternatives to Google's Products and Services examines your options to migrate from the Google ecosystem with open source Linux alternatives.|
|Essential Linux system tools looks at small, indispensable utilities, useful for system administrators as well as regular users.|
|Linux utilities to maximise your productivity. Small, indispensable tools, useful for anyone running a Linux machine.|
|Home computers became commonplace in the 1980s. Emulate home computers such as the ZX81, Amstrad CPC, and ZX Spectrum.|
|Now and Then examines how promising open source software fared over the years.|
|Linux at Home looks at a range of home activities where Linux can play its part, making the most of our time at home, keeping active and engaged.|
|Linux Candy opens up to the lighter side of Linux. Have some fun!|
|Best Free Android Apps. There's a strict eligibility criteria for inclusion in this series|
|These best free books accelerate your learning of every programming language|
|These free tutorials offer the perfect tonic to the free programming books series|
|Stars and Stripes is an occasional series looking at the impact of Linux in the USA|