https://github.com/idiap/finitestatetransducers.jl

Play with Weighted Finite State Transducers (WFST) in the Julia language.
https://github.com/idiap/finitestatetransducers.jl

finite-state-transducers hidden-markov-models speech-recognition wfst

Last synced: about 2 months ago
JSON representation

Play with Weighted Finite State Transducers (WFST) in the Julia language.

• Host: GitHub
• URL: https://github.com/idiap/finitestatetransducers.jl
• Owner: idiap
• License: other
• Created: 2021-02-09T14:17:39.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2022-11-02T14:15:08.000Z (about 2 years ago)
• Last Synced: 2024-10-10T17:47:43.075Z (2 months ago)
• Topics: finite-state-transducers, hidden-markov-models, speech-recognition, wfst
• Language: Julia
• Homepage:
• Size: 252 KB
• Stars: 4
• Watchers: 4
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# FiniteStateTransducers.jl

[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://idiap.github.io/FiniteStateTransducers.jl/stable/)

[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://idiap.github.io/FiniteStateTransducers.jl/dev/)

[![codecov](https://codecov.io/gh/idiap/FiniteStateTransducers.jl/branch/main/graph/badge.svg?token=0W3034W0C3)](https://codecov.io/gh/idiap/FiniteStateTransducers.jl)

[![DOI](https://zenodo.org/badge/337427658.svg)](https://zenodo.org/badge/latestdoi/337427658)

Play with Weighted Finite State Transducers (WFSTs) using the Julia language.

WFSTs provide a powerful framework that assigns a weight (e.g. probability) to conversions of symbol sequences. 

WFSTs are used in many applications such as speech recognition, natural language processing and machine learning.

This package takes a lot of inspiration from [OpenFST](http://openfst.org/twiki/bin/view/FST/DeterminizeDoc).

FiniteStateTransducers is still in an early development stage, see the documentation for currently available features and the issues for the missing ones.

An application of WFSTs can be found in the data preparation of the [TIDIGITS recipe](https://github.com/idiap/TIDIGITSRecipe.jl).