mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
a741de7cf6
* Adding Support for Yoruba * test text * Updated test string. * Fixing encoding declaration. * Adding encoding to stop_words.py * Added contributor agreement and removed iranlowo. * Added removed test files and removed iranlowo to keep project bare. * Returned CONTRIBUTING.md to default state. * Added delted conftest entries * Tidy up and auto-format * Revert CONTRIBUTING.md Co-authored-by: Ines Montani <ines@ines.io>
27 lines
1.3 KiB
Python
27 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
"""
|
|
Example sentences to test spaCy and its language models.
|
|
|
|
>>> from spacy.lang.yo.examples import sentences
|
|
>>> docs = nlp.pipe(sentences)
|
|
"""
|
|
|
|
# 1. https://yo.wikipedia.org/wiki/Wikipedia:%C3%80y%E1%BB%8Dk%C3%A0_p%C3%A0t%C3%A0k%C3%AC
|
|
# 2.https://yo.wikipedia.org/wiki/Oj%C3%BAew%C3%A9_%C3%80k%E1%BB%8D%CC%81k%E1%BB%8D%CC%81
|
|
# 3. https://www.bbc.com/yoruba
|
|
|
|
sentences = [
|
|
"Ìjọba Tanzania fi Ajìjàgbara Ọmọ Orílẹ̀-èdèe Uganda sí àtìmọ́lé",
|
|
"Olúṣẹ́gun Ọbásanjọ́, tí ó jẹ́ Ààrẹ ìjọba ológun àná (láti ọdún 1976 sí 1979), tí ó sì tún ṣe Ààrẹ ìjọba alágbádá tí ìbò gbé wọlé (ní ọdún 1999 sí 2007), kúndùn láti máa bu ẹnu àtẹ́ lu àwọn "
|
|
"ètò ìjọba Ààrẹ orílẹ̀-èdè Nàìjíríà tí ó jẹ tẹ̀lé e.",
|
|
"Akin Alabi rán ẹnu mọ́ agbárá Adárí Òsìsẹ̀, àwọn ọmọ Nàìjíríà dẹnu bò ó",
|
|
"Ta ló leè dúró s'ẹ́gbẹ̀ẹ́ Okunnu láì rẹ́rìín?",
|
|
"Dídarapọ̀ mọ́n ìpolongo",
|
|
"Bi a se n so, omobinrin ni oruko ni ojo kejo bee naa ni omokunrin ni oruko ni ojo kesan.",
|
|
"Oríṣìíríṣìí nǹkan ló le yọrí sí orúkọ tí a sọ ọmọ",
|
|
"Gbogbo won ni won ni oriki ti won",
|
|
]
|