Skip to content

Latest commit

 

History

History
28 lines (19 loc) · 691 Bytes

README.md

File metadata and controls

28 lines (19 loc) · 691 Bytes

Georgian Word2Vec

This is Gensim Word2Vec model trained on Georgian Wikipedia text corpus gathered from Wikipedia dump file.

Requirements

You need Python 3.5 or later to run this project.

Code in this repository requires Gensim Python library to run.

$ pip install --upgrade gensim

Usage

  1. Download pretrained weights from release page.
  2. Unzip weights in project folder.

Example of getting word embedding:

$ python test_word_vector.py

Example of getting word similarity using embeddings:

$ python test_similar_words.py