Deep-Learning-Based-Sinhala-English-Language-Identifier
We can't exactly separate the Sinhala and English words by only using Unicode. It is not 100% accurate because of the issues like some characters of the Sinhala language are not correctly defined in Unicode. Ex:- 'āļ' and etc. Therefore we can use a deep learning based technique to correctly identify Sinhala and English words. This model uses character sequence feature to train. Therefore, we can even predict Singlish words from this model. That is an extra benefit of using this model.
