In this notebook, I'll construct a character-level LSTM with PyTorch. The network will train character by character on some text, then generate new text character by character. As an example, I will train on Harry Potter. This model will be able to generate new text based on the text from the book!
This network is based off of Andrej Karpathy's post on RNNs and implementation in Torch.
This project was done as part of Pytorch Scholarship provided by Udacity and Facebook. Some of the code in the notebook is provided by Udacity.