Raw data
{
"_id": null,
"home_page": "https://github.com/amir-zeldes/RFTokenizer",
"name": "rftokenizer",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "NLP, tokenization, segmentation, morphology, morphological, Hebrew, Arabic, Coptic, word, splitting",
"author": "Amir Zeldes",
"author_email": "amir.zeldes@georgetown.edu",
"download_url": "https://files.pythonhosted.org/packages/f6/b8/e59a7a7157f41957bf5b3c506436f92a7e3deb8cae1994234a026027bf9d/rftokenizer-2.3.0.tar.gz",
"platform": null,
"description": "",
"bugtrack_url": null,
"license": "Apache License, Version 2.0",
"summary": "A character-wise tokenizer for morphologically rich languages",
"version": "2.3.0",
"project_urls": {
"Download": "https://github.com/amir-zeldes/RFTokenizer/releases/tag/v2.3.0",
"Homepage": "https://github.com/amir-zeldes/RFTokenizer"
},
"split_keywords": [
"nlp",
" tokenization",
" segmentation",
" morphology",
" morphological",
" hebrew",
" arabic",
" coptic",
" word",
" splitting"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f6b8e59a7a7157f41957bf5b3c506436f92a7e3deb8cae1994234a026027bf9d",
"md5": "ac6fd46af252a350e12f5fb93f766515",
"sha256": "ab4151b45b30b67a03a04da7569ec23c07e89ff438d9afbbbb965419587880d2"
},
"downloads": -1,
"filename": "rftokenizer-2.3.0.tar.gz",
"has_sig": false,
"md5_digest": "ac6fd46af252a350e12f5fb93f766515",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 77855123,
"upload_time": "2024-12-17T19:05:30",
"upload_time_iso_8601": "2024-12-17T19:05:30.899674Z",
"url": "https://files.pythonhosted.org/packages/f6/b8/e59a7a7157f41957bf5b3c506436f92a7e3deb8cae1994234a026027bf9d/rftokenizer-2.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-17 19:05:30",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "amir-zeldes",
"github_project": "RFTokenizer",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "scikit-learn",
"specs": [
[
"==",
"1.3.2"
]
]
},
{
"name": "joblib",
"specs": [
[
"==",
"1.3.2"
]
]
},
{
"name": "numpy",
"specs": []
},
{
"name": "pandas",
"specs": [
[
"==",
"2.1.2"
]
]
},
{
"name": "xgboost",
"specs": [
[
"==",
"2.0.3"
]
]
},
{
"name": "hyperopt",
"specs": []
},
{
"name": "flair",
"specs": [
[
"==",
"0.13.0"
]
]
}
],
"lcname": "rftokenizer"
}