There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Repository Details
An intelligent "afro-centric" language recognition/detection/identification software that has been trained with datasets from three indigenous Nigerian languages(Hausa,Igbo,Yoruba) and English Language.The software is able to accurately predict the language of any random text/document supplied to the system.This was built with two supervised machine learning algorithms(Naive Bayes Classifier and the K-Nearest Neighbour[kNN] algorithm.Although I have been limited greatly by unavailability of training data in many of Nigerian languages,I hope to make this more robust by enabling the software to predict more than 500 Nigerian languages and to also translate from one language to another.