spaCy/website/meta/languages.json
Adriane Boyd 497a708c71
Docs for v3.3 (#10628)
* Temporarily disable CI tests

* Start v3.3 website updates

* Add trainable lemmatizer to pipeline design

* Fix Vectors.most_similar

* Add floret vector info to pipeline design

* Add Lower and Upper Sorbian

* Add span to sidebar

* Work on release notes

* Copy from release notes

* Update pipeline design graphic

* Upgrading note about Doc.from_docs

* Add tables and details

* Update website/docs/models/index.md

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Fix da lemma acc

* Add minimal intro, various updates

* Round lemma acc

* Add section on floret / word lists

* Add new pipelines table, minor edits

* Fix displacy spans example title

* Clarify adding non-trainable lemmatizer

* Update adding-languages URLs

* Revert "Temporarily disable CI tests"

This reverts commit 1dee505920.

* Spell out words/sec

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2022-04-28 14:09:35 +02:00

579 lines
15 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"languages": [
{
"code": "af",
"name": "Afrikaans"
},
{
"code": "ar",
"name": "Arabic",
"example": "هذه جملة",
"has_examples": true
},
{
"code": "bg",
"name": "Bulgarian",
"example": "Това е изречение",
"has_examples": true
},
{
"code": "bn",
"name": "Bengali",
"has_examples": true
},
{
"code": "ca",
"name": "Catalan",
"example": "Això és una frase.",
"has_examples": true,
"models": [
"ca_core_news_sm",
"ca_core_news_md",
"ca_core_news_lg",
"ca_core_news_trf"
]
},
{
"code": "cs",
"name": "Czech",
"has_examples": true
},
{
"code": "da",
"name": "Danish",
"example": "Dette er en sætning.",
"has_examples": true,
"models": [
"da_core_news_sm",
"da_core_news_md",
"da_core_news_lg",
"da_core_news_trf"
]
},
{
"code": "de",
"name": "German",
"models": [
"de_core_news_sm",
"de_core_news_md",
"de_core_news_lg",
"de_dep_news_trf"
],
"example": "Dies ist ein Satz.",
"has_examples": true
},
{
"code": "dsb",
"name": "Lower Sorbian",
"has_examples": true
},
{
"code": "el",
"name": "Greek",
"models": [
"el_core_news_sm",
"el_core_news_md",
"el_core_news_lg"
],
"example": "Αυτή είναι μια πρόταση.",
"has_examples": true
},
{
"code": "en",
"name": "English",
"models": [
"en_core_web_sm",
"en_core_web_md",
"en_core_web_lg",
"en_core_web_trf"
],
"example": "This is a sentence.",
"has_examples": true
},
{
"code": "es",
"name": "Spanish",
"models": [
"es_core_news_sm",
"es_core_news_md",
"es_core_news_lg",
"es_dep_news_trf"
],
"example": "Esto es una frase.",
"has_examples": true
},
{
"code": "et",
"name": "Estonian"
},
{
"code": "eu",
"name": "Basque",
"has_examples": true
},
{
"code": "fa",
"name": "Persian",
"has_examples": true
},
{
"code": "fi",
"name": "Finnish",
"has_examples": true,
"models": [
"fi_core_news_sm",
"fi_core_news_md",
"fi_core_news_lg"
]
},
{
"code": "fr",
"name": "French",
"models": [
"fr_core_news_sm",
"fr_core_news_md",
"fr_core_news_lg",
"fr_dep_news_trf"
],
"example": "C'est une phrase.",
"has_examples": true
},
{
"code": "ga",
"name": "Irish"
},
{
"code": "gu",
"name": "Gujarati",
"has_examples": true
},
{
"code": "he",
"name": "Hebrew",
"example": "זהו משפט.",
"has_examples": true
},
{
"code": "hi",
"name": "Hindi",
"example": "यह एक वाक्य है।",
"has_examples": true
},
{
"code": "hr",
"name": "Croatian",
"has_examples": true
},
{
"code": "hsb",
"name": "Upper Sorbian",
"has_examples": true
},
{
"code": "hu",
"name": "Hungarian",
"example": "Ez egy mondat.",
"has_examples": true
},
{
"code": "hy",
"name": "Armenian",
"has_examples": true
},
{
"code": "id",
"name": "Indonesian",
"example": "Ini adalah sebuah kalimat.",
"has_examples": true
},
{
"code": "is",
"name": "Icelandic"
},
{
"code": "it",
"name": "Italian",
"models": [
"it_core_news_sm",
"it_core_news_md",
"it_core_news_lg"
],
"example": "Questa è una frase.",
"has_examples": true
},
{
"code": "ja",
"name": "Japanese",
"models": [
"ja_core_news_sm",
"ja_core_news_md",
"ja_core_news_lg",
"ja_core_news_trf"
],
"dependencies": [
{
"name": "SudachiPy",
"url": "https://github.com/WorksApplications/SudachiPy"
}
],
"example": "これは文章です。",
"has_examples": true
},
{
"code": "kn",
"name": "Kannada",
"has_examples": true
},
{
"code": "ko",
"name": "Korean",
"dependencies": [
{
"name": "mecab-ko",
"url": "https://bitbucket.org/eunjeon/mecab-ko/src/master/README.md"
},
{
"name": "mecab-ko-dic",
"url": "https://bitbucket.org/eunjeon/mecab-ko-dic"
},
{
"name": "natto-py",
"url": "https://github.com/buruzaemon/natto-py"
}
],
"example": "이것은 문장입니다.",
"has_examples": true,
"models": [
"ko_core_news_sm",
"ko_core_news_md",
"ko_core_news_lg"
]
},
{
"code": "ky",
"name": "Kyrgyz",
"example": "Адамга эң кыйыны — күн сайын адам болуу",
"has_examples": true
},
{
"code": "lb",
"name": "Luxembourgish",
"has_examples": true
},
{
"code": "lij",
"name": "Ligurian",
"example": "Sta chì a l'é unna fraxe.",
"has_examples": true
},
{
"code": "lt",
"name": "Lithuanian",
"has_examples": true,
"models": [
"lt_core_news_sm",
"lt_core_news_md",
"lt_core_news_lg"
]
},
{
"code": "lv",
"name": "Latvian"
},
{
"code": "mk",
"name": "Macedonian",
"models": [
"mk_core_news_sm",
"mk_core_news_md",
"mk_core_news_lg"
]
},
{
"code": "ml",
"name": "Malayalam",
"has_examples": true
},
{
"code": "mr",
"name": "Marathi"
},
{
"code": "nb",
"name": "Norwegian Bokmål",
"example": "Dette er en setning.",
"has_examples": true,
"models": [
"nb_core_news_sm",
"nb_core_news_md",
"nb_core_news_lg"
]
},
{
"code": "ne",
"name": "Nepali",
"has_examples": true
},
{
"code": "nl",
"name": "Dutch",
"models": [
"nl_core_news_sm",
"nl_core_news_md",
"nl_core_news_lg"
],
"example": "Dit is een zin.",
"has_examples": true
},
{
"code": "pl",
"name": "Polish",
"example": "To jest zdanie.",
"has_examples": true,
"models": [
"pl_core_news_sm",
"pl_core_news_md",
"pl_core_news_lg"
]
},
{
"code": "pt",
"name": "Portuguese",
"models": [
"pt_core_news_sm",
"pt_core_news_md",
"pt_core_news_lg"
],
"example": "Esta é uma frase.",
"has_examples": true
},
{
"code": "ro",
"name": "Romanian",
"example": "Aceasta este o propoziție.",
"has_examples": true,
"models": [
"ro_core_news_sm",
"ro_core_news_md",
"ro_core_news_lg"
]
},
{
"code": "ru",
"name": "Russian",
"has_examples": true,
"dependencies": [
{
"name": "pymorphy2",
"url": "https://github.com/kmike/pymorphy2"
}
],
"models": [
"ru_core_news_sm",
"ru_core_news_md",
"ru_core_news_lg"
]
},
{
"code": "sa",
"name": "Sanskrit",
"has_examples": true
},
{
"code": "si",
"name": "Sinhala",
"example": "මෙය වාක්‍යයකි.",
"has_examples": true
},
{
"code": "sk",
"name": "Slovak",
"has_examples": true
},
{
"code": "sl",
"name": "Slovenian"
},
{
"code": "sq",
"name": "Albanian",
"example": "Kjo është një fjali.",
"has_examples": true
},
{
"code": "sr",
"name": "Serbian",
"has_examples": true
},
{
"code": "sv",
"name": "Swedish",
"has_examples": true,
"models": [
"sv_core_news_sm",
"sv_core_news_md",
"sv_core_news_lg"
]
},
{
"code": "ta",
"name": "Tamil",
"has_examples": true
},
{
"code": "te",
"name": "Telugu",
"example": "ఇది ఒక వాక్యం.",
"has_examples": true
},
{
"code": "th",
"name": "Thai",
"dependencies": [
{
"name": "pythainlp",
"url": "https://github.com/wannaphongcom/pythainlp"
}
],
"example": "นี่คือประโยค",
"has_examples": true
},
{
"code": "tl",
"name": "Tagalog"
},
{
"code": "tn",
"name": "Setswana",
"has_examples": true
},
{
"code": "tr",
"name": "Turkish",
"example": "Bu bir cümledir.",
"has_examples": true
},
{
"code": "tt",
"name": "Tatar",
"has_examples": true
},
{
"code": "uk",
"name": "Ukrainian",
"has_examples": true,
"dependencies": [
{
"name": "pymorphy2",
"url": "https://github.com/kmike/pymorphy2"
}
]
},
{
"code": "ur",
"name": "Urdu",
"example": "یہ ایک جملہ ہے",
"has_examples": true
},
{
"code": "vi",
"name": "Vietnamese",
"dependencies": [
{
"name": "Pyvi",
"url": "https://github.com/trungtv/pyvi"
}
]
},
{
"code": "xx",
"name": "Multi-language",
"models": [
"xx_ent_wiki_sm",
"xx_sent_ud_sm"
],
"example": "This is a sentence about Facebook."
},
{
"code": "yo",
"name": "Yoruba",
"has_examples": true
},
{
"code": "zh",
"name": "Chinese",
"models": [
"zh_core_web_sm",
"zh_core_web_md",
"zh_core_web_lg",
"zh_core_web_trf"
],
"dependencies": [
{
"name": "Jieba",
"url": "https://github.com/fxsjy/jieba"
},
{
"name": "spacy-pkuseg",
"url": "https://github.com/explosion/spacy-pkuseg"
}
],
"has_examples": true
}
],
"licenses": [
{
"id": "CC BY 4.0",
"url": "https://creativecommons.org/licenses/by/4.0/"
},
{
"id": "CC BY-SA",
"url": "https://creativecommons.org/licenses/by-sa/3.0/"
},
{
"id": "CC BY-SA 3.0",
"url": "https://creativecommons.org/licenses/by-sa/3.0/"
},
{
"id": "CC BY-SA 4.0",
"url": "https://creativecommons.org/licenses/by-sa/4.0/"
},
{
"id": "CC BY-NC",
"url": "https://creativecommons.org/licenses/by-nc/3.0/"
},
{
"id": "CC BY-NC 3.0",
"url": "https://creativecommons.org/licenses/by-nc/3.0/"
},
{
"id": "CC BY-NC 4.0",
"url": "https://creativecommons.org/licenses/by-nc/4.0/"
},
{
"id": "CC-BY-NC-SA 3.0",
"url": "https://creativecommons.org/licenses/by-nc-sa/3.0/"
},
{
"id": "GPL",
"url": "https://www.gnu.org/licenses/gpl.html"
},
{
"id": "GPU GPL 3.0",
"url": "https://www.gnu.org/licenses/gpl-3.0.en.html"
},
{
"id": "LGPL",
"url": "https://www.gnu.org/licenses/lgpl.html"
},
{
"id": "MIT",
"url": "https://opensource.org/licenses/MIT"
},
{
"id": "LGPL-LR",
"url": "https://github.com/UniversalDependencies/UD_French-Sequoia/blob/master/LICENSE.txt"
}
]
}