karimistella/South-African-Language-Identification

Language Identification using NLP # South-African-Language-Identification Language Identification using NLP This is a notebook on Language Identification. The text prepocessing, model training and application of trained model on test set can all be found in the jupyter notebook Language_Identification_stella. 'hack14' is a csv file containing the predictions on the test set with no labels. 'train_set' is the data used for training. 'test_set' is the testing data with no labels used for testing the model. The languages identified using the models are South African. There are 11 distinct languages. More information is in the jupyter notebook language_identification_stella.