Upload folder using huggingface_hub

files/languages_iso.csv

@@ -0,0 +1,184 @@
+Language,LangCode
+Abkhazian,ab
+Afar,aa
+Afrikaans,af
+Akan,ak
+Albanian,sq
+Amharic,am
+Arabic,ar
+Aragonese,an
+Armenian,hy
+Assamese,as
+Avaric,av
+Avestan,ae
+Aymara,ay
+Azerbaijani,az
+Bambara,bm
+Bashkir,ba
+Basque,eu
+Belarusian,be
+Bengali,bn
+Bislama,bi
+Bosnian,bs
+Breton,br
+Bulgarian,bg
+Burmese,my
+"Catalan, Valencian",ca
+Chamorro,ch
+Chechen,ce
+"Chichewa, Chewa, Nyanja",ny
+Chinese,zh
+"Church Slavonic, Old Slavonic, Old Church Slavonic",cu
+Chuvash,cv
+Cornish,kw
+Corsican,co
+Cree,cr
+Croatian,hr
+Czech,cs
+Danish,da
+"Divehi, Dhivehi, Maldivian",dv
+"Dutch, Flemish",nl
+Dzongkha,dz
+English,en
+Esperanto,eo
+Estonian,et
+Ewe,ee
+Faroese,fo
+Fijian,fj
+Finnish,fi
+French,fr
+Western Frisian,fy
+Fulah,ff
+"Gaelic, Scottish Gaelic",gd
+Galician,gl
+Ganda,lg
+Georgian,ka
+German,de
+"Greek, Modern (1453–)",el
+"Kalaallisut, Greenlandic",kl
+Guarani,gn
+Gujarati,gu
+"Haitian, Haitian Creole",ht
+Hausa,ha
+Hebrew,he
+Herero,hz
+Hindi,hi
+Hiri Motu,ho
+Hungarian,hu
+Icelandic,is
+Ido,io
+Igbo,ig
+Indonesian,id
+Interlingua (International Auxiliary Language Association),ia
+"Interlingue, Occidental",ie
+Inuktitut,iu
+Inupiaq,ik
+Irish,ga
+Italian,it
+Japanese,ja
+Javanese,jv
+Kannada,kn
+Kanuri,kr
+Kashmiri,ks
+Kazakh,kk
+Central Khmer,km
+"Kikuyu, Gikuyu",ki
+Kinyarwanda,rw
+"Kirghiz, Kyrgyz",ky
+Komi,kv
+Kongo,kg
+Korean,ko
+"Kuanyama, Kwanyama",kj
+Kurdish,ku
+Lao,lo
+Latin,la
+Latvian,lv
+"Limburgan, Limburger, Limburgish",li
+Lingala,ln
+Lithuanian,lt
+Luba-Katanga,lu
+"Luxembourgish, Letzeburgesch",lb
+Macedonian,mk
+Malagasy,mg
+Malay,ms
+Malayalam,ml
+Maltese,mt
+Manx,gv
+Maori,mi
+Marathi,mr
+Marshallese,mh
+Mongolian,mn
+Nauru,na
+"Navajo, Navaho",nv
+North Ndebele,nd
+South Ndebele,nr
+Ndonga,ng
+Nepali,ne
+Norwegian,no
+Norwegian Bokmål,nb
+Norwegian Nynorsk,nn
+"Sichuan Yi, Nuosu",ii
+Occitan,oc
+Ojibwa,oj
+Oriya,or
+Oromo,om
+"Ossetian, Ossetic",os
+Pali,pi
+"Pashto, Pushto",ps
+Persian,fa
+Polish,pl
+Portuguese,pt
+"Punjabi, Panjabi",pa
+Quechua,qu
+"Romanian, Moldavian, Moldovan",ro
+Romansh,rm
+Rundi,rn
+Russian,ru
+Northern Sami,se
+Samoan,sm
+Sango,sg
+Sanskrit,sa
+Sardinian,sc
+Serbian,sr
+Shona,sn
+Sindhi,sd
+"Sinhala, Sinhalese",si
+Slovak,sk
+Slovenian,sl
+Somali,so
+Southern Sotho,st
+"Spanish, Castilian",es
+Sundanese,su
+Swahili,sw
+Swati,ss
+Swedish,sv
+Tagalog,tl
+Tahitian,ty
+Tajik,tg
+Tamil,ta
+Tatar,tt
+Telugu,te
+Thai,th
+Tibetan,bo
+Tigrinya,ti
+Tonga (Tonga Islands),to
+Tsonga,ts
+Tswana,tn
+Turkish,tr
+Turkmen,tk
+Twi,tw
+"Uighur, Uyghur",ug
+Ukrainian,uk
+Urdu,ur
+Uzbek,uz
+Venda,ve
+Vietnamese,vi
+Volapük,vo
+Walloon,wa
+Welsh,cy
+Wolof,wo
+Xhosa,xh
+Yiddish,yi
+Yoruba,yo
+"Zhuang, Chuang",za
+Zulu,zu

files/languages_tesseract.csv

@@ -0,0 +1,127 @@
+Language,LangCode
+Afrikaans,afr
+Amharic,amh
+Arabic,ara
+Assamese,asm
+Azerbaijani,aze
+Azerbaijani - Cyrilic,aze_cyrl
+Belarusian,bel
+Bengali,ben
+Tibetan,bod
+Bosnian,bos
+Breton,bre
+Bulgarian,bul
+Catalan; Valencian,cat
+Cebuano,ceb
+Czech,ces
+Chinese - Simplified,chi_sim
+Chinese - Traditional,chi_tra
+Cherokee,chr
+Corsican,cos
+Welsh,cym
+Danish,dan
+Danish - Fraktur (contrib),dan_frak
+German,deu
+German - Fraktur (contrib),deu_frak
+Dzongkha,dzo
+"Greek, Modern (1453-)",ell
+English,eng
+"English, Middle (1100-1500)",enm
+Esperanto,epo
+Math / equation detection module,equ
+Estonian,est
+Basque,eus
+Faroese,fao
+Persian,fas
+Filipino (old - Tagalog),fil
+Finnish,fin
+French,fra
+German - Fraktur,frk
+"French, Middle (ca.1400-1600)",frm
+Western Frisian,fry
+Scottish Gaelic,gla
+Irish,gle
+Galician,glg
+"Greek, Ancient (to 1453) (contrib)",grc
+Gujarati,guj
+Haitian; Haitian Creole,hat
+Hebrew,heb
+Hindi,hin
+Croatian,hrv
+Hungarian,hun
+Armenian,hye
+Inuktitut,iku
+Indonesian,ind
+Icelandic,isl
+Italian,ita
+Italian - Old,ita_old
+Javanese,jav
+Japanese,jpn
+Kannada,kan
+Georgian,kat
+Georgian - Old,kat_old
+Kazakh,kaz
+Central Khmer,khm
+Kirghiz; Kyrgyz,kir
+Kurmanji (Kurdish - Latin Script),kmr
+Korean,kor
+Korean (vertical),kor_vert
+Kurdish (Arabic Script),kur
+Lao,lao
+Latin,lat
+Latvian,lav
+Lithuanian,lit
+Luxembourgish,ltz
+Malayalam,mal
+Marathi,mar
+Macedonian,mkd
+Maltese,mlt
+Mongolian,mon
+Maori,mri
+Malay,msa
+Burmese,mya
+Nepali,nep
+Dutch; Flemish,nld
+Norwegian,nor
+Occitan (post 1500),oci
+Oriya,ori
+Orientation and script detection module,osd
+Panjabi; Punjabi,pan
+Polish,pol
+Portuguese,por
+Pushto; Pashto,pus
+Quechua,que
+Romanian; Moldavian; Moldovan,ron
+Russian,rus
+Sanskrit,san
+Sinhala; Sinhalese,sin
+Slovak,slk
+Slovak - Fraktur (contrib),slk_frak
+Slovenian,slv
+Sindhi,snd
+Spanish; Castilian,spa
+Spanish; Castilian - Old,spa_old
+Albanian,sqi
+Serbian,srp
+Serbian - Latin,srp_latn
+Sundanese,sun
+Swahili,swa
+Swedish,swe
+Syriac,syr
+Tamil,tam
+Tatar,tat
+Telugu,tel
+Tajik,tgk
+Tagalog (new - Filipino),tgl
+Thai,tha
+Tigrinya,tir
+Tonga,ton
+Turkish,tur
+Uighur; Uyghur,uig
+Ukrainian,ukr
+Urdu,urd
+Uzbek,uzb
+Uzbek - Cyrilic,uzb_cyrl
+Vietnamese,vie
+Yiddish,yid
+Yoruba,yor