# based on :

https://github.com/LeanManager/NLP-PyTorch/blob/master/Character-Level%20LSTM%20with%20PyTorch.ipynb https://github.com/karpathy/char-rnn#tips-and-tricks http://karpathy.github.io/2015/05/21/rnn-effectiveness/

# prepare the dataset

convert epub to text (calibre cli)> ebook-convert livre.epub livre.txt

# show how much GPU used for training watch -d -n 0.5 nvidia-smi