Metadata-Version: 2.1
Name: cc-net
Version: 0.0.0
Summary: Tools to download and clean Common Crawl
Home-page: https://github.com/facebookresearch/cc_net
Author: Guillaume Wenzek
Author-email: guw@fb.com
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/facebookresearch/cc_net/issues
Project-URL: Source Code, https://github.com/facebookresearch/cc_net
Keywords: common crawl dataset
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3.7
Requires-Python: >=3.7
Requires-Dist: beautifulsoup4 (>=4.7.1)
Requires-Dist: pandas (>=0.23.4)
Requires-Dist: requests (>=2.22.0)
Requires-Dist: fasttext (>=0.9.1)
Requires-Dist: sentencepiece (>=0.1.82)
Requires-Dist: func-argparse (>=1.0.3)
Requires-Dist: sacremoses
Provides-Extra: dev
Requires-Dist: mypy (>=0.730) ; extra == 'dev'
Requires-Dist: pytest ; extra == 'dev'
Requires-Dist: black ; extra == 'dev'
Requires-Dist: isort ; extra == 'dev'
Provides-Extra: slurm
Requires-Dist: submitit ; extra == 'slurm'
Provides-Extra: tools
Requires-Dist: sentence-splitter ; extra == 'tools'

UNKNOWN


