FastText is a lightweight library designed to help build scalable solutions for text representation and classification. It works on standard, generic hardware and can even fit on smartphones and small computers through functionality that reduces memory consumed by fastText models.
FastText is designed to be simple to use for developers, domain experts, and students. It's dedicated to text classification and learning word representations, and was designed to allow for quick model iteration and refinement without specialized hardware. fastText models can be trained on more than a billion words on any multicore CPU in less than a few minutes.
It includes pre-trained models learned on Wikipedia and in over 157 different languages. fastText can be used as a command line, linked to a C++ application, or used as a library for use cases from experimentation and prototyping to production.
Get source code and build fastText using make (preferred), cmake, or Python.
$ git clone https://github.com/facebookresearch/fastText.git $ cd fastText $ make
Review documentation and tutorials to familiarize yourself with word representation learning and text classification in fastText.
Download pre-trained models and iterate on them or build and train new models.