.gitignore

# macOS
.DS_Store

# Python
__pycache__/

# development
config.sh
*.bbprojectd/
TODO
TODO/
/zz-*/
/00-*/
/results-2023-11-19/
/results-2023-12/
/clean-*-test*/
/tubelex-en-V0/
/tubelex-en-remote/
/*.ftz

# jtubespeech & tubelex output
/jtubespeech
/jtubespeech-subtitles
/tubelex-ja-channels.tsv
/*.xz
/*.zip
/*.tsv
/*.out
/tubelex-frequency-2024-07-15
/tubelex-frequency-2024-07-23-es
tubelex-*-removed-addresses.json

# The corpus is not public due to copyright...
/corpus/*
# ...except ideo ids and metadata:
!/corpus/videos-*.csv

# SubIMDB data, LaboroTVSpeech, HKUST-MTCS data
/SubIMDB_All_Individual.tar.xz
/SubIMDB_All_Individual.tar
/SubIMDB_All_Individual/
/laborotvspeech.zip
/laborotvspeech
/LDC2005T32

# experiments/LCP data
/data/*
/data/downloads/*
!/data/subtlex-es.tsv.xz
!/data/chinese-familiarity.tsv.xz
!/data/indonesian-subjective-frequency.csv.xz
!/data/os*.tsv.xz
!/data/os_README.txt
!/data/es-words.*.txt
!/data/mrc.csv
!/data/mrc_README.txt
!/data/github-images
/experiments/zz-*
/experiments/models/*
/experiments/output/*
/experiments/output.tsv
/experiments/cache/*

# large files
/fasttext/
/kenlm/