This repository presents #edai ongoing NLP research projects to empower endangered African Languages.
Accepted at the AfricaNLP workshop of EACL 2021, OkwuGbé is a step towards building speech recognition systems for African low-resourced languages. Using Fon and Igbo as our case study, we conduct a comprehensive linguistic analysis of each language and describe the creation of end-to-end, deep neural network-based speech recognition models for both languages.
The Fon and Igbo implementations are respectively Fon-here and Igbo-here. The full talk of the paper is available at https://www.youtube.com/watch?v=2p42k7SmIAU
2- Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Language
Accepted at EACL 2021, WEB is a human-involved super-words tokenization strategy to create a better representative vocabulary for training. WEB is at the root of the first version of FFRTranslate. Read fully about FFR: French-Fon Neural Machine Translation here.
The full talk of WEB is available at https://www.youtube.com/watch?v=wnUKIATuuQE
Thsi repository is owned and maintained by Bonaventure Dossou and Chris Emezue. You can read about our common and personal research at Bonaventure Dossou - Semantic Scholar and Chris Emezue
We are open to donations. Please consider donating Advocating for African Languages preservation or by FFR Translate - PayPal