Machine Translation for Africa

• UpdatedJun 14, 2022
• Lua

A repository for publicly/freely available Natural Language Processing (NLP) datasets for African languages.

• UpdatedApr 26, 2024

Yorùbá language training text for NLP, ASR and TTS tasks

• UpdatedMar 3, 2023
• Python

AfriSenti-SemEval Shared Task 12: Sentiment Analysis for African languages :https://afrisenti-semeval.github.io/

• UpdatedJan 10, 2024
• Jupyter Notebook

SemEval2024-task 11: Bridging the Gap in Text-Based Emotion Detection

• UpdatedMar 23, 2025
• Jupyter Notebook

Masakhane Web is a translation web application for solely African Languages.

• UpdatedAug 11, 2023
• Jupyter Notebook

This is a repository for NaijaSenti. A Lacuna Funded Project for the development of sentiment corpus for four Nigerian languages: Igbo, Hausa, Yoruba and Pidgin.

• UpdatedJan 10, 2024

AfroLID, a powerful neural toolkit for African languages identification which covers 517 African languages.

• UpdatedMar 10, 2025
• Python

Automatic Diacritic Restoration of Yorùbá language Text

• UpdatedJul 25, 2024
• Python

Cross-lingual Language Model (XLM) pretraining and Model-Agnostic Meta-Learning (MAML) for fast adaptation of deep networks

• UpdatedMar 26, 2021
• Jupyter Notebook

Ìrànlọ́wọ́ is a utility library for analysis & (pre)processing of Yorùbá text →https://pypi.org/project/iranlowo

• UpdatedDec 10, 2022
• Python

stoplists for African languages generated from the ASP corpus

• UpdatedJan 16, 2016
• Ruby

Introduction to "Tencent’s Multilingual Machine Translation System for WMT22 Large-Scale African Languages".

• UpdatedApr 7, 2023
• Shell

Website that hosts the African Voices projects. Users can download datasets and synthesizers, and synthesize speech in African languages

• UpdatedJun 12, 2022
• Python

A Python based utility for Swahili and English number to words conversion.

• UpdatedDec 1, 2019
• Python

Sankofa Display is a typeface that draws inspiration from African art styles, with a focus on straight-line geometric designs.

• UpdatedMay 10, 2024
• Python

The dataset contains editions from the South African government magazine Vuk'uzenzele. Data was scraped from PDFs that have been placed in the data/raw folder. The PDFS were obtained from the Vuk'uzenzele website.

• UpdatedDec 6, 2023
• Jupyter Notebook

Adinkra Symbols API - meanings of adinkra symbols, symbol images and synopsis around them

• UpdatedDec 12, 2022
• JavaScript

AfricanWordNet: Implementation of WordNets for African languages. Citation paper "Practical Approach on Implementation of WordNets for South African Languages"https://www.aclweb.org/anthology/2021.gwc-1.3.pdf

• UpdatedMar 29, 2021
• HTML

Code + data for the EMNLP'20 publication "Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages"

• UpdatedDec 16, 2021
• Python