LSTMs are great for timeseries forecasting and sequence predictions. This makes them appropriate for natural language prediction. This tutorial explains the process of training an LSTM network on English text and predicting letters based on the training.
Reference: https://www.gutenberg.org/
Text file link: http://www.gutenberg.org/ebooks/236
Code generated in the video can be downloaded from here:
https://github.com/bnsreenu/python_for_microscopists