A minimalist, general-purpose programming language based on meta-programming and parse tree rewrites

API to Informal dictionary for the idiomatic expressions that each Brazilian region It has

Recaffeinating Java ☕️ with custom semantics and extensions

Transliteration for languages and dialects

The amazing 🐕will normalize non-standard Finnish/Swedish and dialectalize standard Finnish!

製作漢字相關語音字典及輸入法，目的只爲保存各地區言語及文化。

Build languages on Python.

Classifier that identifies Greek text as Cypriot Greek or Standard Modern Greek

NorDial is a project that aims to create resources and collect knowledge about the state of written Norwegian dialects on the web, specifically in social media.

Holon Platform JDBC Datastore module. This is the JDBC implementation of the Datastore API, with relational expressions and transactions support, along with a full Spring and Spring Boot integration.

Corpus-based language and dialect mapping

This repository contains resources from the paper A Survey of Large Language Models for Arabic Language and its Dialects

[EACL 2021] Self-training Pretrained LMs for Zero- and Few-shot Arabic Sequence Labeling

Extend JDBC types support for Apache Spark.

Extending dialectal support for Chinese voicebanks of Synthesizer V

A compilation of the most varied dialects spoken around Brazil

Internal Domain Specific (Multi)Modeling js framework

The codebase for the "ALDi: Quantifying the Arabic Level of Dialectness of Text" paper accepted to EMNLP 2023.

A shell script is a computer program designed to be run by the Unix shell, a command-line interpreter. The various dialects of shell scripts are considered to be scripting languages. Typical operations performed by shell scripts include file manipulation, program execution, and printing text

Translating websites via moravskyprekladac

An atlas of Central Kurdish dialects + a simple game to detect dialects

Code and dataset used to train dialect adapters for decoder models.

Chinese2025（广韵查询，方言查询，常见拟音搜索功能，永明体检测，古体诗注韵，古诗注声调、韵）

Lightweight bopomofo keyboard extension for Google Chrome.

Repository for the paper "A Multilingual, Culture-First Approach to Addressing Misgendering in LLM Applications"

Master Thesis on "Analyzing Slot and Intent Detection for Upper German Dialects via Zero-Shot Transfer Learning" and Paper on "Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study"

English to Egyptian Arabic Movies translation. A ground-up implementation of a 98M-param Encoder-Decoder model. Specialized for subtitles and slang, it’s trained on a 700k-sentence corpus to catch the dialectal nuances that standard models miss.

TugaPhone is a Python library that phonemizes arbitrary Portuguese text across major Lusophone dialects (pt-PT, pt-BR, pt-AO, pt-MZ, pt-TL). It uses a curated phonetic lexicon plus a rule-based fallback to deliver plausible phoneme transcriptions while preserving dialectal variation.

Real-time Swiss German voice chat application supporting 8 dialects. Multi-AI provider support (Groq, Gemini, OpenAI) with optimized latency pipeline.

přeložení do moravštiny / translating into Moravian