madlad-400-translate / langmap /langid_mapping.py
Daryl Lim
fix: address code review findings
7633dda
Raw
History Blame
25.1 kB
# Auto-generated by scripts/generate_langmap.py from MADLAD-400 paper Table 9 (Section A.1)
# Source: https://arxiv.org/pdf/2309.04662
# 418 languages with training data (excludes 79 self-audit omissions)
#
# To regenerate:
# python scripts/generate_langmap.py <path-to-paper.pdf>
langid_to_language = {
"<2ach>": {"name": "Acoli", "region": "Africa"},
"<2ada>": {"name": "Adangme", "region": "Africa"},
"<2adh>": {"name": "Adhola", "region": "Africa"},
"<2aa>": {"name": "Afar", "region": "Africa"},
"<2af>": {"name": "Afrikaans", "region": "Africa"},
"<2alz>": {"name": "Alur", "region": "Africa"},
"<2am>": {"name": "Amharic", "region": "Africa"},
"<2bm>": {"name": "Bambara", "region": "Africa"},
"<2bci>": {"name": "Baoulé", "region": "Africa"},
"<2bas>": {"name": "Basa (Cameroon)", "region": "Africa"},
"<2bim>": {"name": "Bimoba", "region": "Africa"},
"<2bqc>": {"name": "Boko (Benin)", "region": "Africa"},
"<2bus>": {"name": "Bokobaru", "region": "Africa"},
"<2bum>": {"name": "Bulu", "region": "Africa"},
"<2ny>": {"name": "Chichewa", "region": "Africa"},
"<2cjk>": {"name": "Chokwe", "region": "Africa"},
"<2cce>": {"name": "Chopi", "region": "Africa"},
"<2dwr>": {"name": "Dawro", "region": "Africa"},
"<2din>": {"name": "Dinka", "region": "Africa"},
"<2tbz>": {"name": "Ditammari", "region": "Africa"},
"<2dov>": {"name": "Dombe", "region": "Africa"},
"<2dyu>": {"name": "Dyula", "region": "Africa"},
"<2ee>": {"name": "Ewe", "region": "Africa"},
"<2fip>": {"name": "Fipa", "region": "Africa"},
"<2fon>": {"name": "Fon", "region": "Africa"},
"<2ff>": {"name": "Fulfulde", "region": "Africa"},
"<2gof>": {"name": "Gofa", "region": "Africa"},
"<2gvl>": {"name": "Gulay", "region": "Africa"},
"<2ha>": {"name": "Hausa", "region": "Africa"},
"<2ibb>": {"name": "Ibibio", "region": "Africa"},
"<2ig>": {"name": "Igbo", "region": "Africa"},
"<2iso>": {"name": "Isoko", "region": "Africa"},
"<2izz>": {"name": "Izii", "region": "Africa"},
"<2kbp>": {"name": "Kabiyè", "region": "Africa"},
"<2kmb>": {"name": "Kimbundu", "region": "Africa"},
"<2rw>": {"name": "Kinyarwanda", "region": "Africa"},
"<2ktu>": {"name": "Kituba (DRC)", "region": "Africa"},
"<2kg>": {"name": "Kongo", "region": "Africa"},
"<2kri>": {"name": "Krio", "region": "Africa"},
"<2kj>": {"name": "Kuanyama", "region": "Africa"},
"<2laj>": {"name": "Lango (Uganda)", "region": "Africa"},
"<2ln>": {"name": "Lingala", "region": "Africa"},
"<2lu>": {"name": "Luba-Katanga", "region": "Africa"},
"<2lg>": {"name": "Luganda", "region": "Africa"},
"<2ffm>": {"name": "Maasina Fulfulde", "region": "Africa"},
"<2mgh>": {"name": "Makhuwa-Meetto", "region": "Africa"},
"<2mg>": {"name": "Malagasy", "region": "Africa"},
"<2mas>": {"name": "Masai", "region": "Africa"},
"<2mfe>": {"name": "Morisien", "region": "Africa"},
"<2nnb>": {"name": "Nande", "region": "Africa"},
"<2niq>": {"name": "Nandi", "region": "Africa"},
"<2nyu>": {"name": "Nyungwe", "region": "Africa"},
"<2nzi>": {"name": "Nzima", "region": "Africa"},
"<2ann>": {"name": "Obolo", "region": "Africa"},
"<2om>": {"name": "Oromo", "region": "Africa"},
"<2rn>": {"name": "Rundi", "region": "Africa"},
"<2sg>": {"name": "Sango", "region": "Africa"},
"<2seh>": {"name": "Sena", "region": "Africa"},
"<2nso>": {"name": "Sepedi", "region": "Africa"},
"<2srr>": {"name": "Serer", "region": "Africa"},
"<2st>": {"name": "Sesotho", "region": "Africa"},
"<2sn>": {"name": "Shona", "region": "Africa"},
"<2so>": {"name": "Somali", "region": "Africa"},
"<2nr>": {"name": "South Ndebele", "region": "Africa"},
"<2spp>": {"name": "Supyire Senoufo", "region": "Africa"},
"<2sus>": {"name": "Susu", "region": "Africa"},
"<2sw>": {"name": "Swahili", "region": "Africa"},
"<2ss>": {"name": "Swati", "region": "Africa"},
"<2ber>": {"name": "Tamazight (Tfng)", "region": "Africa"},
"<2tdx>": {"name": "Tandroy-Mahafaly Malagasy", "region": "Africa"},
"<2teo>": {"name": "Teso", "region": "Africa"},
"<2tll>": {"name": "Tetela", "region": "Africa"},
"<2ti>": {"name": "Tigrinya", "region": "Africa"},
"<2tiv>": {"name": "Tiv", "region": "Africa"},
"<2ts>": {"name": "Tsonga", "region": "Africa"},
"<2tsc>": {"name": "Tswa", "region": "Africa"},
"<2tn>": {"name": "Tswana", "region": "Africa"},
"<2ak>": {"name": "Twi", "region": "Africa"},
"<2ve>": {"name": "Venda", "region": "Africa"},
"<2wal>": {"name": "Wolaytta", "region": "Africa"},
"<2wo>": {"name": "Wolof", "region": "Africa"},
"<2xh>": {"name": "Xhosa", "region": "Africa"},
"<2yo>": {"name": "Yoruba", "region": "Africa"},
"<2zne>": {"name": "Zande", "region": "Africa"},
"<2dje>": {"name": "Zarma", "region": "Africa"},
"<2zu>": {"name": "Zulu", "region": "Africa"},
"<2agr>": {"name": "Aguaruna", "region": "Americas"},
"<2cni>": {"name": "Asháninka", "region": "Americas"},
"<2kwi>": {"name": "Awa-Cuaiquer", "region": "Americas"},
"<2quy>": {"name": "Ayacucho Quechua", "region": "Americas"},
"<2ay>": {"name": "Aymara", "region": "Americas"},
"<2bzj>": {"name": "Belize Kriol English", "region": "Americas"},
"<2qvc>": {"name": "Cajamarca Quechua", "region": "Americas"},
"<2qxr>": {"name": "Cañar H. Quichua", "region": "Americas"},
"<2maz>": {"name": "Central Mazahua", "region": "Americas"},
"<2chr>": {"name": "Cherokee", "region": "Americas"},
"<2ctu>": {"name": "Chol", "region": "Americas"},
"<2cac>": {"name": "Chuj", "region": "Americas"},
"<2gui>": {"name": "E. Bolivian Guaraní", "region": "Americas"},
"<2nhe>": {"name": "E. Huasteca Nahuatl", "region": "Americas"},
"<2djk>": {"name": "E. Maroon Creole", "region": "Americas"},
"<2sja>": {"name": "Epena", "region": "Americas"},
"<2cab>": {"name": "Garifuna", "region": "Americas"},
"<2guh>": {"name": "Guahibo", "region": "Americas"},
"<2gub>": {"name": "Guajajára", "region": "Americas"},
"<2gn>": {"name": "Guarani", "region": "Americas"},
"<2amu>": {"name": "Guerrero Amuzgo", "region": "Americas"},
"<2ngu>": {"name": "Guerrero Nahuatl", "region": "Americas"},
"<2gyn>": {"name": "Guyanese Creole English", "region": "Americas"},
"<2ht>": {"name": "Haitian Creole", "region": "Americas"},
"<2haw>": {"name": "Hawaiian", "region": "Americas"},
"<2qub>": {"name": "Huallaga Huánuco Quechua", "region": "Americas"},
"<2hus>": {"name": "Huastec", "region": "Americas"},
"<2qvi>": {"name": "Imbabura H. Quichua", "region": "Americas"},
"<2inb>": {"name": "Inga", "region": "Americas"},
"<2iu>": {"name": "Inuktitut", "region": "Americas"},
"<2jam>": {"name": "Jamaican Creole English", "region": "Americas"},
"<2kl>": {"name": "Kalaallisut", "region": "Americas"},
"<2cak>": {"name": "Kaqchikel", "region": "Americas"},
"<2kek>": {"name": "Kekchí", "region": "Americas"},
"<2tlh>": {"name": "Klingon", "region": "Americas"},
"<2quc>": {"name": "K’iche’", "region": "Americas"},
"<2quf>": {"name": "Lambayeque Quechua", "region": "Americas"},
"<2mam>": {"name": "Mam", "region": "Americas"},
"<2arn>": {"name": "Mapudungun", "region": "Americas"},
"<2miq>": {"name": "Mískito", "region": "Americas"},
"<2emp>": {"name": "N. Emberá", "region": "Americas"},
"<2qvz>": {"name": "N. Pastaza Quichua", "region": "Americas"},
"<2nv>": {"name": "Navajo", "region": "Americas"},
"<2gym>": {"name": "Ngäbere", "region": "Americas"},
"<2zxx>": {"name": "Noise", "region": "Americas"},
"<2oj>": {"name": "Ojibwa", "region": "Americas"},
"<2pap>": {"name": "Papiamento", "region": "Americas"},
"<2jac>": {"name": "Popti’", "region": "Americas"},
"<2qu>": {"name": "Quechua", "region": "Americas"},
"<2otq>": {"name": "Querétaro Otomi", "region": "Americas"},
"<2rcf>": {"name": "Réunion Creole French", "region": "Americas"},
"<2quh>": {"name": "S. Bolivian Quechua", "region": "Americas"},
"<2qup>": {"name": "S. Pastaza Quechua", "region": "Americas"},
"<2cuk>": {"name": "San Blas Kuna", "region": "Americas"},
"<2srm>": {"name": "Saramaccan", "region": "Americas"},
"<2crs>": {"name": "Seselwa Creole French", "region": "Americas"},
"<2shp>": {"name": "Shipibo-Conibo", "region": "Americas"},
"<2jiv>": {"name": "Shuar", "region": "Americas"},
"<2srn>": {"name": "Sranan Tongo", "region": "Americas"},
"<2acf>": {"name": "St Lucian Creole French", "region": "Americas"},
"<2tca>": {"name": "Ticuna", "region": "Americas"},
"<2toj>": {"name": "Tojolabal", "region": "Americas"},
"<2tzh>": {"name": "Tzeltal", "region": "Americas"},
"<2tzo>": {"name": "Tzotzil", "region": "Americas"},
"<2tzj>": {"name": "Tz’utujil", "region": "Americas"},
"<2knj>": {"name": "W. Kanjobal", "region": "Americas"},
"<2guc>": {"name": "Wayuu", "region": "Americas"},
"<2noa>": {"name": "Woun Meu", "region": "Americas"},
"<2yua>": {"name": "Yucateco", "region": "Americas"},
"<2zap>": {"name": "Zapotec", "region": "Americas"},
"<2az>": {"name": "Azerbaijani", "region": "Central Asia"},
"<2ba>": {"name": "Bashkir", "region": "Central Asia"},
"<2kaa-Latn>": {"name": "Kara-Kalpak (Latn)", "region": "Central Asia"},
"<2kk>": {"name": "Kazakh", "region": "Central Asia"},
"<2ky>": {"name": "Kyrghyz", "region": "Central Asia"},
"<2tg>": {"name": "Tajik", "region": "Central Asia"},
"<2tk>": {"name": "Turkmen", "region": "Central Asia"},
"<2uz>": {"name": "Uzbek", "region": "Central Asia"},
"<2yue>": {"name": "Cantonese", "region": "East Asia"},
"<2dz>": {"name": "Dzongkha", "region": "East Asia"},
"<2ja>": {"name": "Japanese", "region": "East Asia"},
"<2ko>": {"name": "Korean", "region": "East Asia"},
"<2zh>": {"name": "Mandarin Chinese", "region": "East Asia"},
"<2mn>": {"name": "Mongolian", "region": "East Asia"},
"<2bo>": {"name": "Tibetan", "region": "East Asia"},
"<2sah>": {"name": "Yakut", "region": "East Asia"},
"<2za>": {"name": "Zhuang", "region": "East Asia"},
"<2ady>": {"name": "Adyghe", "region": "Europe"},
"<2sq>": {"name": "Albanian", "region": "Europe"},
"<2grc>": {"name": "Ancient Greek", "region": "Europe"},
"<2hy>": {"name": "Armenian", "region": "Europe"},
"<2frp>": {"name": "Arpitan", "region": "Europe"},
"<2av>": {"name": "Avar", "region": "Europe"},
"<2eu>": {"name": "Basque", "region": "Europe"},
"<2be>": {"name": "Belarusian", "region": "Europe"},
"<2bs>": {"name": "Bosnian", "region": "Europe"},
"<2br>": {"name": "Breton", "region": "Europe"},
"<2bg>": {"name": "Bulgarian", "region": "Europe"},
"<2bua>": {"name": "Buryat", "region": "Europe"},
"<2rmc>": {"name": "Carpathian Romani", "region": "Europe"},
"<2ca>": {"name": "Catalan", "region": "Europe"},
"<2ce>": {"name": "Chechen", "region": "Europe"},
"<2cv>": {"name": "Chuvash", "region": "Europe"},
"<2kw>": {"name": "Cornish", "region": "Europe"},
"<2co>": {"name": "Corsican", "region": "Europe"},
"<2crh>": {"name": "Crimean Tatar", "region": "Europe"},
"<2hr>": {"name": "Croatian", "region": "Europe"},
"<2cs>": {"name": "Czech", "region": "Europe"},
"<2da>": {"name": "Danish", "region": "Europe"},
"<2nl>": {"name": "Dutch", "region": "Europe"},
"<2en>": {"name": "English", "region": "Europe"},
"<2myv>": {"name": "Erzya", "region": "Europe"},
"<2eo>": {"name": "Esperanto", "region": "Europe"},
"<2et>": {"name": "Estonian", "region": "Europe"},
"<2fo>": {"name": "Faroese", "region": "Europe"},
"<2fi>": {"name": "Finnish", "region": "Europe"},
"<2fr>": {"name": "French", "region": "Europe"},
"<2gag>": {"name": "Gagauz", "region": "Europe"},
"<2gl>": {"name": "Galician", "region": "Europe"},
"<2ka>": {"name": "Georgian", "region": "Europe"},
"<2de>": {"name": "German", "region": "Europe"},
"<2el>": {"name": "Greek", "region": "Europe"},
"<2mrj>": {"name": "Hill Mari", "region": "Europe"},
"<2hu>": {"name": "Hungarian", "region": "Europe"},
"<2is>": {"name": "Icelandic", "region": "Europe"},
"<2ga>": {"name": "Irish", "region": "Europe"},
"<2it>": {"name": "Italian", "region": "Europe"},
"<2kbd>": {"name": "Kabardian", "region": "Europe"},
"<2xal>": {"name": "Kalmyk", "region": "Europe"},
"<2kaa>": {"name": "Kara-Kalpak", "region": "Europe"},
"<2krc>": {"name": "Karachay-Balkar", "region": "Europe"},
"<2kjh>": {"name": "Khakas", "region": "Europe"},
"<2kv>": {"name": "Komi", "region": "Europe"},
"<2koi>": {"name": "Komi-Permyak", "region": "Europe"},
"<2kum>": {"name": "Kumyk", "region": "Europe"},
"<2ltg>": {"name": "Latgalian", "region": "Europe"},
"<2la>": {"name": "Latin", "region": "Europe"},
"<2lv>": {"name": "Latvian", "region": "Europe"},
"<2lt>": {"name": "Lithuanian", "region": "Europe"},
"<2lb>": {"name": "Luxembourgish", "region": "Europe"},
"<2mk>": {"name": "Macedonian", "region": "Europe"},
"<2mt>": {"name": "Maltese", "region": "Europe"},
"<2gv>": {"name": "Manx", "region": "Europe"},
"<2chm>": {"name": "Meadow Mari", "region": "Europe"},
"<2mdf>": {"name": "Moksha", "region": "Europe"},
"<2se>": {"name": "N. Sami", "region": "Europe"},
"<2nog>": {"name": "Nogai", "region": "Europe"},
"<2no>": {"name": "Norwegian", "region": "Europe"},
"<2oc>": {"name": "Occitan", "region": "Europe"},
"<2ang>": {"name": "Old English", "region": "Europe"},
"<2os>": {"name": "Ossetian", "region": "Europe"},
"<2pl>": {"name": "Polish", "region": "Europe"},
"<2pt>": {"name": "Portuguese", "region": "Europe"},
"<2rom>": {"name": "Romani", "region": "Europe"},
"<2ro>": {"name": "Romanian", "region": "Europe"},
"<2rm>": {"name": "Romansh", "region": "Europe"},
"<2ru>": {"name": "Russian", "region": "Europe"},
"<2alt>": {"name": "S. Altai", "region": "Europe"},
"<2stq>": {"name": "Saterfriesisch", "region": "Europe"},
"<2gd>": {"name": "Scottish Gaelic", "region": "Europe"},
"<2sr>": {"name": "Serbian", "region": "Europe"},
"<2sk>": {"name": "Slovak", "region": "Europe"},
"<2sl>": {"name": "Slovenian", "region": "Europe"},
"<2es>": {"name": "Spanish", "region": "Europe"},
"<2sv>": {"name": "Swedish", "region": "Europe"},
"<2gsw>": {"name": "Swiss German", "region": "Europe"},
"<2tab>": {"name": "Tabassaran", "region": "Europe"},
"<2tt>": {"name": "Tatar", "region": "Europe"},
"<2tyv>": {"name": "Tuvinian", "region": "Europe"},
"<2udm>": {"name": "Udmurt", "region": "Europe"},
"<2uk>": {"name": "Ukrainian", "region": "Europe"},
"<2vec>": {"name": "Venetian", "region": "Europe"},
"<2fy>": {"name": "W. Frisian", "region": "Europe"},
"<2wa>": {"name": "Walloon", "region": "Europe"},
"<2cy>": {"name": "Welsh", "region": "Europe"},
"<2ar>": {"name": "Arabic", "region": "Middle East & North Africa"},
"<2bgp>": {"name": "E. Baluchi", "region": "Middle East & North Africa"},
"<2mey>": {"name": "Hassaniyya", "region": "Middle East & North Africa"},
"<2he>": {"name": "Hebrew", "region": "Middle East & North Africa"},
"<2ks>": {"name": "Kashmiri", "region": "Middle East & North Africa"},
"<2ku>": {"name": "Kurdish (Kurmanji)", "region": "Middle East & North Africa"},
"<2ckb>": {"name": "Kurdish (Sorani)", "region": "Middle East & North Africa"},
"<2lrc>": {"name": "N. Luri", "region": "Middle East & North Africa"},
"<2ps>": {"name": "Pashto", "region": "Middle East & North Africa"},
"<2fa>": {"name": "Persian", "region": "Middle East & North Africa"},
"<2luz>": {"name": "S. Luri", "region": "Middle East & North Africa"},
"<2skr>": {"name": "Saraiki", "region": "Middle East & North Africa"},
"<2sd>": {"name": "Sindhi", "region": "Middle East & North Africa"},
"<2syr>": {"name": "Syriac", "region": "Middle East & North Africa"},
"<2tks>": {"name": "Takestani", "region": "Middle East & North Africa"},
"<2tr>": {"name": "Turkish", "region": "Middle East & North Africa"},
"<2ur>": {"name": "Urdu", "region": "Middle East & North Africa"},
"<2ug>": {"name": "Uyghur", "region": "Middle East & North Africa"},
"<2yi>": {"name": "Yiddish", "region": "Middle East & North Africa"},
"<2zza>": {"name": "Zaza", "region": "Middle East & North Africa"},
"<2abt>": {"name": "Ambulas", "region": "Oceania"},
"<2bi>": {"name": "Bislama", "region": "Oceania"},
"<2ape>": {"name": "Bukiyip", "region": "Oceania"},
"<2ch>": {"name": "Chamorro", "region": "Oceania"},
"<2chk>": {"name": "Chuukese", "region": "Oceania"},
"<2mps>": {"name": "Dadibi", "region": "Oceania"},
"<2enq>": {"name": "Enga", "region": "Oceania"},
"<2hif>": {"name": "Fiji Hindi", "region": "Oceania"},
"<2fj>": {"name": "Fijian", "region": "Oceania"},
"<2gil>": {"name": "Gilbertese", "region": "Oceania"},
"<2ho>": {"name": "Hiri Motu", "region": "Oceania"},
"<2hui>": {"name": "Huli", "region": "Oceania"},
"<2kos>": {"name": "Kosraean", "region": "Oceania"},
"<2ksd>": {"name": "Kuanua", "region": "Oceania"},
"<2mi>": {"name": "Maori", "region": "Oceania"},
"<2mh>": {"name": "Marshallese", "region": "Oceania"},
"<2meu>": {"name": "Motu", "region": "Oceania"},
"<2tuc>": {"name": "Mutu", "region": "Oceania"},
"<2pau>": {"name": "Palauan", "region": "Oceania"},
"<2pis>": {"name": "Pijin", "region": "Oceania"},
"<2pon>": {"name": "Pohnpeian", "region": "Oceania"},
"<2rwo>": {"name": "Rawa", "region": "Oceania"},
"<2hvn>": {"name": "Sabu", "region": "Oceania"},
"<2sm>": {"name": "Samoan", "region": "Oceania"},
"<2twu>": {"name": "Termanu", "region": "Oceania"},
"<2to>": {"name": "Tonga (Tonga Islands)", "region": "Oceania"},
"<2tvl>": {"name": "Tuvalu", "region": "Oceania"},
"<2ubu>": {"name": "Umbu-Ungu", "region": "Oceania"},
"<2yap>": {"name": "Yapese", "region": "Oceania"},
"<2as>": {"name": "Assamese", "region": "South Asia"},
"<2awa>": {"name": "Awadhi", "region": "South Asia"},
"<2bn>": {"name": "Bengali", "region": "South Asia"},
"<2bho>": {"name": "Bhojpuri", "region": "South Asia"},
"<2brx>": {"name": "Bodo (India)", "region": "South Asia"},
"<2hne>": {"name": "Chhattisgarhi", "region": "South Asia"},
"<2dv>": {"name": "Dhivehi", "region": "South Asia"},
"<2taj>": {"name": "E. Tamang", "region": "South Asia"},
"<2gbm>": {"name": "Garhwali", "region": "South Asia"},
"<2gom>": {"name": "Goan Konkani", "region": "South Asia"},
"<2gu>": {"name": "Gujarati", "region": "South Asia"},
"<2hi>": {"name": "Hindi", "region": "South Asia"},
"<2bjj>": {"name": "Kanauji", "region": "South Asia"},
"<2kn>": {"name": "Kannada", "region": "South Asia"},
"<2kha>": {"name": "Khasi", "region": "South Asia"},
"<2trp>": {"name": "Kok Borok", "region": "South Asia"},
"<2mag>": {"name": "Magahi", "region": "South Asia"},
"<2mai>": {"name": "Maithili", "region": "South Asia"},
"<2ml>": {"name": "Malayalam", "region": "South Asia"},
"<2mr>": {"name": "Marathi", "region": "South Asia"},
"<2mni>": {"name": "Meiteilon (Manipuri)", "region": "South Asia"},
"<2mtr>": {"name": "Mewari", "region": "South Asia"},
"<2lus>": {"name": "Mizo", "region": "South Asia"},
"<2ne>": {"name": "Nepali", "region": "South Asia"},
"<2new>": {"name": "Newari", "region": "South Asia"},
"<2noe>": {"name": "Nimadi", "region": "South Asia"},
"<2or>": {"name": "Odia (Oriya)", "region": "South Asia"},
"<2pa>": {"name": "Punjabi", "region": "South Asia"},
"<2raj>": {"name": "Rajasthani", "region": "South Asia"},
"<2sa>": {"name": "Sanskrit", "region": "South Asia"},
"<2smt>": {"name": "Simte", "region": "South Asia"},
"<2si>": {"name": "Sinhala", "region": "South Asia"},
"<2suz>": {"name": "Sunwar", "region": "South Asia"},
"<2sjp>": {"name": "Surjapuri", "region": "South Asia"},
"<2syl>": {"name": "Sylheti", "region": "South Asia"},
"<2ta>": {"name": "Tamil", "region": "South Asia"},
"<2te>": {"name": "Telugu", "region": "South Asia"},
"<2tcy>": {"name": "Tulu", "region": "South Asia"},
"<2ace>": {"name": "Achinese", "region": "Southeast Asia"},
"<2msm>": {"name": "Agusan Manobo", "region": "Southeast Asia"},
"<2ahk>": {"name": "Akha", "region": "Southeast Asia"},
"<2ban>": {"name": "Balinese", "region": "Southeast Asia"},
"<2bgz>": {"name": "Banggai", "region": "Southeast Asia"},
"<2akb>": {"name": "Batak Angkola", "region": "Southeast Asia"},
"<2btx>": {"name": "Batak Karo", "region": "Southeast Asia"},
"<2bts>": {"name": "Batak Simalungun", "region": "Southeast Asia"},
"<2bbc>": {"name": "Batak Toba", "region": "Southeast Asia"},
"<2bew>": {"name": "Betawi", "region": "Southeast Asia"},
"<2jvn>": {"name": "Caribbean Javanese", "region": "Southeast Asia"},
"<2ceb>": {"name": "Cebuano", "region": "Southeast Asia"},
"<2bik>": {"name": "Central Bikol", "region": "Southeast Asia"},
"<2mel>": {"name": "Central Melanau", "region": "Southeast Asia"},
"<2cbk>": {"name": "Chavacano", "region": "Southeast Asia"},
"<2bru>": {"name": "E. Bru", "region": "Southeast Asia"},
"<2cfm>": {"name": "Falam Chin", "region": "Southeast Asia"},
"<2fil>": {"name": "Filipino", "region": "Southeast Asia"},
"<2gor>": {"name": "Gorontalo", "region": "Southeast Asia"},
"<2cnh>": {"name": "Hakha Chin", "region": "Southeast Asia"},
"<2hil>": {"name": "Hiligaynon", "region": "Southeast Asia"},
"<2hmn>": {"name": "Hmong", "region": "Southeast Asia"},
"<2iba>": {"name": "Iban", "region": "Southeast Asia"},
"<2ilo>": {"name": "Ilocano", "region": "Southeast Asia"},
"<2id>": {"name": "Indonesian", "region": "Southeast Asia"},
"<2ium>": {"name": "Iu Mien", "region": "Southeast Asia"},
"<2jax>": {"name": "Jambi Malay", "region": "Southeast Asia"},
"<2jv>": {"name": "Javanese", "region": "Southeast Asia"},
"<2kac>": {"name": "Kachin", "region": "Southeast Asia"},
"<2dtp>": {"name": "Kadazan Dusun", "region": "Southeast Asia"},
"<2meo>": {"name": "Kedah Malay", "region": "Southeast Asia"},
"<2ify>": {"name": "Keley-IKallahan", "region": "Southeast Asia"},
"<2km>": {"name": "Khmer", "region": "Southeast Asia"},
"<2kjg>": {"name": "Khmu", "region": "Southeast Asia"},
"<2krj>": {"name": "Kinaray-A", "region": "Southeast Asia"},
"<2mkn>": {"name": "Kupang Malay", "region": "Southeast Asia"},
"<2lhu>": {"name": "Lahu", "region": "Southeast Asia"},
"<2lo>": {"name": "Lao", "region": "Southeast Asia"},
"<2mad>": {"name": "Madurese", "region": "Southeast Asia"},
"<2mak>": {"name": "Makasar", "region": "Southeast Asia"},
"<2ms>": {"name": "Malay", "region": "Southeast Asia"},
"<2xmm>": {"name": "Manado Malay", "region": "Southeast Asia"},
"<2mqy>": {"name": "Manggarai", "region": "Southeast Asia"},
"<2mrw>": {"name": "Maranao", "region": "Southeast Asia"},
"<2msb>": {"name": "Masbatenyo", "region": "Southeast Asia"},
"<2mbt>": {"name": "Matigsalug Manobo", "region": "Southeast Asia"},
"<2min>": {"name": "Minangkabau", "region": "Southeast Asia"},
"<2mnw>": {"name": "Mon", "region": "Southeast Asia"},
"<2my>": {"name": "Myanmar (Burmese)", "region": "Southeast Asia"},
"<2nij>": {"name": "Ngaju", "region": "Southeast Asia"},
"<2nia>": {"name": "Nias", "region": "Southeast Asia"},
"<2nut>": {"name": "Nung (Viet Nam)", "region": "Southeast Asia"},
"<2pck>": {"name": "Paite Chin", "region": "Southeast Asia"},
"<2pam>": {"name": "Pampanga", "region": "Southeast Asia"},
"<2pag>": {"name": "Pangasinan", "region": "Southeast Asia"},
"<2prk>": {"name": "Parauk", "region": "Southeast Asia"},
"<2rki>": {"name": "Rakhine", "region": "Southeast Asia"},
"<2msi>": {"name": "Sabah Malay", "region": "Southeast Asia"},
"<2sxn>": {"name": "Sangir", "region": "Southeast Asia"},
"<2shn>": {"name": "Shan", "region": "Southeast Asia"},
"<2su>": {"name": "Sundanese", "region": "Southeast Asia"},
"<2ksw>": {"name": "S’gaw Karen", "region": "Southeast Asia"},
"<2tsg>": {"name": "Tausug", "region": "Southeast Asia"},
"<2tet>": {"name": "Tetum", "region": "Southeast Asia"},
"<2th>": {"name": "Thai", "region": "Southeast Asia"},
"<2sda>": {"name": "Toraja-Sa’dan", "region": "Southeast Asia"},
"<2tyz>": {"name": "Tày", "region": "Southeast Asia"},
"<2ppk>": {"name": "Uma", "region": "Southeast Asia"},
"<2vi>": {"name": "Vietnamese", "region": "Southeast Asia"},
"<2war>": {"name": "Waray (Philippines)", "region": "Southeast Asia"},
}