ju-bezdek / open-subtitles-lang-detection

1. Prepare virtual enviroment

 pipenv install

2. get from open-subtitiles-dataset (if you have it) and copy it into

./open-subtitles-dataset

    /train

    /text

or recreate it

 python main.py prepare

(downloads lot's of data from internet)

3. run training

python main.py train local