This project is inspired from Andrej's Makemore(Bigram model) where i trained a simple feed forward neural network on a dataset containing Indian names. After training the model it generates baby name ideas that all sound name-like, but are not already existing names and not only human names we can generate anything like company names,pet names etc.
Preprocessed the data to remove any unwanted characters other than english alphabets,removed blank spaces,duplicate entries,added a dataset of female names with the original dataset and shuffled the whole dataset for uniform training. Male Dataset + Female Dataset = Cleaned_Dataset