1. Run blather.py, this will generate a 'sentences.corpus' file based on sentences in the 'commands' file
2. quit blather (there is a good chance it will just segfault)
3. go to http://www.speech.cs.cmu.edu/tools/lmtool-new.html and upload the sentences.corpus file
4. download the resulting XXXX.lm file to the 'language' directory and rename to file to 'lm'
5. download the resulting XXXX.dic file to the 'language' directory and rename to file to 'dic'
6. run blather.py
7. start talking