MFST: A Python OpenFST Wrapper With Support for Custom Semirings and Jupyter Notebooks

TL;DR

mFST is a Python wrapper for OpenFST that uniquely supports custom semirings, enabling advanced FST modeling and neural integration, demonstrated through API showcase and neuralized FST example.

Contribution

This work introduces mFST, the first Python wrapper for OpenFST with support for custom semirings, facilitating neural network integration.

Findings

mFST exposes all OpenFST methods in Python.

Supports defining custom semirings for FSTs.

Demonstrated neuralized FST with PyTorch.

Abstract

This paper introduces mFST, a new Python library for working with Finite-State Machines based on OpenFST. mFST is a thin wrapper for OpenFST and exposes all of OpenFST's methods for manipulating FSTs. Additionally, mFST is the only Python wrapper for OpenFST that exposes OpenFST's ability to define a custom semirings. This makes mFST ideal for developing models that involve learning the weights on a FST or creating neuralized FSTs. mFST has been designed to be easy to get started with and has been previously used in homework assignments for a NLP class as well in projects for integrating FSTs and neural networks. In this paper, we exhibit mFST API and how to use mFST to build a simple neuralized FST with PyTorch.