sentencex
Version:
Sentence segmentation library
244 lines (243 loc) • 4.78 kB
JSON
{
"ab": ["ru"],
"abs": ["id"],
"ace": ["id"],
"ady": ["ady-cyrl"],
"aeb": ["aeb-arab"],
"aeb-arab": ["ar"],
"aln": ["sq"],
"alt": ["ru"],
"ami": ["zh-hant"],
"an": ["es"],
"anp": ["hi"],
"arn": ["es"],
"arq": ["ar"],
"ary": ["ar"],
"arz": ["ar"],
"ast": ["es"],
"atj": ["fr"],
"av": ["ru"],
"avk": ["fr", "es", "ru"],
"awa": ["hi"],
"ay": ["es"],
"azb": ["fa"],
"ba": ["ru"],
"ban": ["id"],
"ban-bali": ["ban"],
"bar": ["de"],
"bbc": ["bbc-latn"],
"bbc-latn": ["id"],
"bcc": ["fa"],
"be-tarask": ["be"],
"bgn": ["fa"],
"bh": ["bho"],
"bi": ["en"],
"bjn": ["id"],
"bm": ["fr"],
"bpy": ["bn"],
"bqi": ["fa"],
"br": ["fr"],
"btm": ["id"],
"bug": ["id"],
"bxr": ["ru"],
"ca": ["oc"],
"cbk-zam": ["es"],
"cdo": ["nan", "zh-hant"],
"ce": ["ru"],
"co": ["it"],
"crh": ["crh-latn"],
"crh-cyrl": ["ru"],
"cs": ["sk"],
"csb": ["pl"],
"cv": ["ru"],
"de-at": ["de"],
"de-ch": ["de"],
"de-formal": ["de"],
"dsb": ["de"],
"dtp": ["ms"],
"dty": ["ne"],
"egl": ["it"],
"eml": ["it"],
"en-ca": ["en"],
"en-gb": ["en"],
"es-419": ["es"],
"es-formal": ["es"],
"ext": ["es"],
"ff": ["fr"],
"fit": ["fi"],
"frc": ["fr"],
"frp": ["fr"],
"frr": ["de"],
"fur": ["it"],
"gag": ["tr"],
"gan": ["gan-hant", "zh-hant", "zh-hans"],
"gan-hans": ["zh-hans"],
"gan-hant": ["zh-hant", "zh-hans"],
"gcr": ["fr"],
"gl": ["pt"],
"glk": ["fa"],
"gn": ["es"],
"gom": ["gom-deva"],
"gom-deva": ["hi"],
"gor": ["id"],
"gsw": ["de"],
"guc": ["es"],
"hak": ["zh-hant"],
"hif": ["hif-latn"],
"hrx": ["de"],
"hsb": ["dsb", "de"],
"ht": ["fr"],
"hu-formal": ["hu"],
"hyw": ["hy"],
"ii": ["zh-cn", "zh-hans"],
"inh": ["ru"],
"io": ["eo"],
"iu": ["ike-cans"],
"jam": ["en"],
"jut": ["da"],
"jv": ["id"],
"kaa": ["kk-latn", "kk-cyrl"],
"kab": ["fr"],
"kbd": ["kbd-cyrl"],
"kbp": ["fr"],
"khw": ["ur"],
"kiu": ["tr"],
"kjp": ["my"],
"kk": ["kk-cyrl"],
"kk-arab": ["kk-cyrl"],
"kk-cn": ["kk-arab", "kk-cyrl"],
"kk-kz": ["kk-cyrl"],
"kk-latn": ["kk-cyrl"],
"kk-tr": ["kk-latn", "kk-cyrl"],
"kl": ["da"],
"ko-kp": ["ko"],
"koi": ["ru"],
"krc": ["ru"],
"krl": ["fi"],
"ks": ["ks-arab"],
"ksh": ["de"],
"ku": ["ku-latn"],
"ku-arab": ["ckb"],
"kum": ["ru"],
"kv": ["ru"],
"lad": ["es"],
"lb": ["de"],
"lbe": ["ru"],
"lez": ["ru", "az"],
"li": ["nl"],
"lij": ["it"],
"liv": ["et"],
"lki": ["fa"],
"lld": ["it", "rm", "fur"],
"lmo": ["pms", "eml", "lij", "vec", "it"],
"ln": ["fr"],
"lrc": ["fa"],
"ltg": ["lv"],
"luz": ["fa"],
"lzh": ["zh-hant"],
"lzz": ["tr"],
"mad": ["id"],
"mai": ["hi"],
"map-bms": ["jv", "id"],
"mdf": ["ru"],
"mg": ["fr"],
"mhr": ["ru"],
"min": ["id"],
"mnw": ["my"],
"mo": ["ro"],
"mrj": ["ru"],
"ms-arab": ["ms"],
"mwl": ["pt"],
"myv": ["ru"],
"mzn": ["fa"],
"nah": ["es"],
"nan": ["cdo", "zh-hant"],
"nap": ["it"],
"nds": ["de"],
"nds-nl": ["nl"],
"nia": ["id"],
"nl-informal": ["nl"],
"nn": ["nb"],
"nrm": ["fr"],
"oc": ["ca", "fr"],
"olo": ["fi"],
"os": ["ru"],
"pcd": ["fr"],
"pdc": ["de"],
"pdt": ["de"],
"pfl": ["de"],
"pih": ["en"],
"pms": ["it"],
"pnt": ["el"],
"pt": ["pt-br"],
"pt-br": ["pt"],
"qu": ["es"],
"qug": ["es"],
"rgn": ["it"],
"rmy": ["ro"],
"roa-tara": ["it"],
"rue": ["uk", "ru"],
"rup": ["ro"],
"ruq": ["ruq-latn", "ro"],
"ruq-cyrl": ["mk"],
"ruq-latn": ["ro"],
"sa": ["hi"],
"sah": ["ru"],
"scn": ["it"],
"sco": ["en"],
"sdc": ["it"],
"sdh": ["cbk", "fa"],
"ses": ["fr"],
"sg": ["fr"],
"sgs": ["lt"],
"sh": ["bs", "sr-el", "hr"],
"shi": ["fr"],
"shy": ["shy-latn"],
"shy-latn": ["fr"],
"sk": ["cs"],
"skr": ["skr-arab"],
"skr-arab": ["ur", "pnb"],
"sli": ["de"],
"smn": ["fi"],
"sr": ["sr-ec"],
"srn": ["nl"],
"stq": ["de"],
"sty": ["ru"],
"su": ["id"],
"szl": ["pl"],
"szy": ["zh-tw", "zh-hant", "zh-hans"],
"tay": ["zh-tw", "zh-hant", "zh-hans"],
"tcy": ["kn"],
"tet": ["pt"],
"tg": ["tg-cyrl"],
"trv": ["zh-tw", "zh-hant", "zh-hans"],
"tt": ["tt-cyrl", "ru"],
"tt-cyrl": ["ru"],
"ty": ["fr"],
"tyv": ["ru"],
"udm": ["ru"],
"ug": ["ug-arab"],
"vec": ["it"],
"vep": ["et"],
"vls": ["nl"],
"vmf": ["de"],
"vot": ["fi"],
"vro": ["et"],
"wa": ["fr"],
"wo": ["fr"],
"wuu": ["zh-hans"],
"xal": ["ru"],
"xmf": ["ka"],
"yi": ["he"],
"za": ["zh-hans"],
"zea": ["nl"],
"zgh": ["kab"],
"zh": ["zh-hans"],
"zh-cn": ["zh-hans"],
"zh-hant": ["zh-hans"],
"zh-hk": ["zh-hant", "zh-hans"],
"zh-mo": ["zh-hk", "zh-hant", "zh-hans"],
"zh-my": ["zh-sg", "zh-hans"],
"zh-sg": ["zh-hans"],
"zh-tw": ["zh-hant", "zh-hans"]
}