I've recently come across TextBlob, which seems like a very neat Natural Language Processing library. http://textblob.readthedocs.org/en/dev/quickstart.html
However, I am concerned because it seems to act as a regular Python string. I have a very large text file, and for example, calling blob.correct() for a very modest text amount takes a very long time. Any feedback on the scale of TextBlob or any alternatives for natural language parsing?