This project is to use parallel Nepali-English corpus alongside word2vec, KNN and local sensitive hashing to translate Nepali language to English and viceversa.
Data source : https://drive.google.com/file/d/1UThfJKJFvDgTu263DNbz-WPNLqoARZ_0/view
Use the .en or .np. to csv translator script available in this repositories to convert all of the files into csv file or simply download the csv files.
In data '.en' represents the English corpus and '.np' represents the Nepalese corpus.