The objective of this project is to use machine learning methods for constructing a LID model which can discriminate 4 languages; English, French, Arabic, Japanese. There are 2 expected phases.
The first phase is constructing a classifier. It is expected to compare the performance of different models, optimize the hyperparameters, and practice of finding the best model.
The second phase is the evaluation of the model in a simulated situation of real life deployment. The objective is to understand the challenge of generalization. It's also expected to analyze the result of the model’s performance and make hypothesis about the weak and strong aspect of models. The competition among models' accuracy can provide a better understanding of performance.