bigscience/SourcingCatalog
8
1{2 "language_groups": {3 "Niger-Congo": "African languages of the Niger-Congo family, incl. Bantu languages",4 "Arabic": "Arabic",5 "Basque": "Basque",6 "Catalan": "Catalan",7 "Chinese": "Chinese",8 "English": "English",9 "French": "French",10 "Indic": "Indic languages, incl. Bengali, Hindi, Urdu...",11 "Indonesian": "Indonesian",12 "Portuguese": "Portuguese",13 "Spanish": "Spanish",14 "Vietnamese": "Vietnamese",15 "Programming Language": "Programming Language"16 },17 "niger_congo_languages": [18 "Akan",19 "Bambara",20 "Chi Chewa",21 "ChiShona",22 "ChiTumbuka",23 "Fon",24 "Igbo",25 "isiZulu",26 "Kinyarwanda",27 "Kikongo",28 "Kikuyu",29 "Kirundi",30 "Lingala",31 "Luganda",32 "Northern Sotho",33 "Sesotho",34 "Setswana",35 "Swahili",36 "Twi",37 "Wolof",38 "Xhosa",39 "Xitsonga",40 "Yoruba"41 ],42 "indic_languages": [43 "Assamese",44 "Bengali",45 "Gujarati",46 "Hindi",47 "Kannada",48 "Malayalam",49 "Marathi",50 "Odia",51 "Punjabi",52 "Telugu",53 "Tamil",54 "Urdu"55 ],56 "arabic": {57 "ar-CLS": "(Arabic (Classic))",58 "ar-MSA": "(Arabic (Modern Standard Arabic))",59 "ar-LEV": "(Arabic (Levant))",60 "ar-NOR": "(Arabic (North Africa))",61 "ar-GLF": "(Arabic (Gulf))",62 "ar-AE": "(Arabic (United Arab Emirates))",63 "ar-BH": "(Arabic (Bahrain))",64 "ar-DJ": "(Arabic (Djibouti))",65 "ar-DZ": "(Arabic (Algeria))",66 "ar-EG": "(Arabic (Egypt))",67 "ar-IQ": "(Arabic (Iraq))",68 "ar-JO": "(Arabic (Jordan))",69 "ar-KM": "(Arabic (Comoros))",70 "ar-KW": "(Arabic (Kuwait))",71 "ar-LB": "(Arabic (Lebanon))",72 "ar-LY": "(Arabic (Libya))",73 "ar-MA": "(Arabic (Morocco))",74 "ar-MR": "(Arabic (Mauritania))",75 "ar-OM": "(Arabic (Oman))",76 "ar-PS": "(Arabic (Palestinian Territories))",77 "ar-QA": "(Arabic (Qatar))",78 "ar-SA": "(Arabic (Saudi Arabia))",79 "ar-SD": "(Arabic (Sudan))",80 "ar-SO": "(Arabic (Somalia))",81 "ar-SS": "(Arabic (South Sudan))",82 "ar-SY": "(Arabic (Syria))",83 "ar-TN": "(Arabic (Tunisia))",84 "ar-YE": "(Arabic (Yemen))"85 }86}87 