Open Source C++ Machine Translation Software

OPolyglot is a fast and fully offline translator that respects your privacy. The application is powered by the robust "Bergamot" engine, allowing you to perform all translations locally on your device without the need for an internet connection. At the current stage of development, OPolyglot offers two key features: Simple Translator: A convenient tool for classic translation of typed or copied text. Screen Translator: A smart feature that allows you to take a screenshot of any screen area, automatically recognize the text (OCR), and instantly translate it. OPolyglot is an excellent assistant for reading foreign documents, playing games, or working with unlocalized applications, all while keeping your data completely secure.

Crow Translate is a simple and lightweight translator written in C++ / Qt that allows you to translate and speak text using Google, Yandex, Bing, LibreTranslate and Lingva translate API. You may also be interested in my library QOnlineTranslator used in this project. Wayland does not support global shortcuts registration, but you can use D-Bus to bind actions in the system settings. For desktop environments that support additional applications actions (KDE, for example) you will see them predefined in the system shortcut settings. You can also use them for X11 sessions, but you need to disable global shortcuts registration in the application settings to avoid conflicts. On Linux to make the application look native on a non-KDE desktop environment, you need to configure Qt applications styling.

Apertium is a toolbox to build open-source shallow-transfer machine translation systems, especially suitable for related language pairs: it includes the engine, maintenance tools, and open linguistic data for several language pairs.

The Arabic Corpus {compiled by Dr. Mourad Abbas ( http://sites.google.com/site/mouradabbas9/corpora ) The corpus Khaleej-2004 contains 5690 documents. It is divided to 4 topics (categories). The corpus Watan-2004 contains 20291 documents organized in 6 topics (categories). Researchers who use these two corpora would mention the two main references: (1) For Watan-2004 corpus ---------------------- M. Abbas, K. Smaili, D. Berkani, (2011) Evaluation of Topic Identification Methods on Arabic Corpora,JOURNAL OF DIGITAL INFORMATION MANAGEMENT,vol. 9, N. 5, pp.185-192. 2) For Khaleej-2004 corpus --------------------------------- M. Abbas, K. Smaili (2005) Comparison of Topic Identification Methods for Arabic Language, RANLP05 : Recent Advances in Natural Language Processing ,pp. 14-17, 21-23 september 2005, Borovets, Bulgary. More useful references to check: ------------------------------------------- https://sites.google.com/site/mouradabbas9/corpora

XBNF Neurotranslator is a powerfull extended BNF grammar language to handle translations. XBNF comes with many features to handle different kind of situations. See [Files] to get the xbnf command binaries among architectures. Blog with all ressources (DockerHub images, documentations, ...): https://damolab.zapto.org/xbnf/ Seek library to get a full set of grammar examples: https://sourceforge.net/projects/xbnf/

GrammarChecker is a utility for instant grammar correction in any text field via keyboard shortcut, powered by Large Language Models (LLM). Grammar Checker utilizes the OpenAI API, supporting both OpenAI and Google Gemini models (It is possible to add other custom models via config), and requires an API key to function. Simply select the text you want to check and trigger the assigned shortcut. Grammar Checker can be automatically launched on startup and run in the system tray. The main window provides a user-friendly interface where you can assign any specific keyboard shortcut for triggering grammar checks or adjust the prompt requirements to align with your specific writing needs, such as translating text into different language or something else.

AzConvert is an open source program to convert different scripts of Azerbaijani language (Latin, Arabic and Cyrillic) to each other. It's written in Qt.

A project that aims to create reusable components (C++ libraries, COM components, and Edit controls) for Phonetic Transliteration of Indian languages, such as Telugu, Tamil, Kannada etc.

Core program and associated utilities for building a machine translation system using the Example-Based paradigm, where previously-translated text is used to infer new translations of previously-unseen text.

Fast Unsupervised Sentence Aligner described in "Improved unsupervised sentence alignment for symmetrical and asymmetrical parallel corpora", COLING 2010. NEWS : release 1.0b : bug fixed (release1.0a deprecated).

IsItQt is a Linux console application to identify if the program was created using Qt and in most cases, using which version of Qt was it created. Article about usage: http://www.cplusplus.com/articles/y3TbqMoL/

JPPL is an experimental, exploratory project aiming at the target of geting better (written) language analyzing software.

mgiza has now moved to github https://github.com/moses-smt/mgiza

Pes is an simple programing language. It has just few basic constructions and it has c-like & pascal-like syntax. The compiler output is Jasmin - an assembler for java virtual machine. It was my school project.

Stanford Phrasal is a state-of-the-art statistical phrase-based machine translation system, written in Java. At its core, it provides much the same functionality as the core of Moses. Distinctive features include: providing an easy to use API for implementing new decoding model features, the ability to translating using phrases that include gaps (Galley et al. 2010), and conditional extraction of phrase-tables and lexical reordering models. Developed by The Natural Language Processing Group at Stanford University, a team of faculty, postdocs, programmers and students who work together on algorithms that allow computers to process and understand human languages. Our work ranges from basic research in computational linguistics to key applications in human language technology, and covers areas such as sentence understanding, automatic question answering, machine translation, syntactic parsing and tagging, sentiment analysis.

Poga is software for processing of formal languages, especially for processing automata and grammars. It has modular architecture, it is programmed in C++ and it doesn't have a GUI (it has CLI).

A tool for large richly annotated parallel corpora preprocessing and Moses phrase-table extraction.

This tool is made to score machine translation performance with the TER metric. This code is based on Snover's algorithm.

This project is a library which provide examples of XBNF grammars. XBNF neurotranslator compiler and ressources available here: https://neurotranslator.sourceforge.io

espeak-tswana is a branch of espeak project implementing Setswana (A Southern African Bantu speaking language) .

A library to convert from Greeklish (aka. Greek written using the Latin alphabet) to real Greek.

This package implements the phrased-based hidden semi-Markov model described: Jesús Andrés-Ferrer, Alfons Juan. A phrase-based hidden semi-Markov approach to machine translation. Procedings of European Association for Machine Translation (EAMT), 2009. pp. 168-175. This project depends on jaf_Utils: http://sourceforge.net/projects/jafutils/ Install it prior installation of jaf_MT.

LR(k) parser generator (k>=0) implementation.

Qt-based Google Translate client.