Wester is an raw, Open Source, quintgram NLP. It's current release (C2) has a 4.5M-token corpus.
As Wester is written fully in python, it runs on any machine, that can use python. Atleast Python 3 is required.
user@pc: cd yourFileLocation/Wester
user@pc: py main.py wester/
├── data/ # Wester's corpus data
├── main.py
├── pipeline.py
├── ngrams.py
├── loader.py
├── tokenizer.py
├── tfidf.py
├── sentiment.py
├── cleaner.py
├── stopwords.py
├── frequency.py
├── OPT-IN.md # Opt-In instructions
├── LICENSE.md
└── README.md
Wester can be used under the GNU General Public License v3.0