! I had mailed you earlier and posted on the mailing list again. So, here's the repo to the basic implemetation of word2vec for sanskrit: https://github.com/erzaliator/SanskritWord2Vec
a) I need to complete it for the entire ramayana corpus and then the rest of the sanskrit corpus. I am on it already.
b) I need to implement get_sims() as well; just as the latin word2vec.py
c) Other tasks are commented in the code itself. This code needs a lot of optimization.
d) All suggestions are open for the modifications.
e) I hope I'm going in the right direction. I shall be awaiting further instructions.
P.S. I am simultaneously going through the beginner's exercises.