Files of Phishing Detection Model will be posted here Firstly we initiated with Data Gathering and found out Dataset present in Kaggle of English Language to Identify Ham or Spam Message is great one. We downloaded that data and initially we were doing manual Translation after that we have used API key of Google translate and Microsoft Translate those files are Coding Files to translate English into Hindi -> The file named Niket,Hindi,Translation.ipynb is responsible for translating Hindi text to English using Google Tanslate API. -> Where as file named Balancing_for_nlp.ipynb is responsible for translation of Hindi text to English using Microsoft Azure API. Then initiated our work of data generation, the translation files are also attached and translation codes too. Then we have did initial data analysis which is mentioned above and it's png file is also present. After that we have started generating vectorise file were stopped words got removed by using different ML libraries for Stopped words removal in Hindi and Telugu. Then Random Forest is seperately made with it's own vectorise file which also mentioned. So simply go through with those Model generarion files first where all models and it's classification report has been showcased and then all the models has been tested in the test.ipynb file. Test cases to check those models are also presented overhere.