Upload 2 files

isolanguages.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93401c6c3822e82ce2d8c79f5365a61c907d76fec54115360d5380360409bba4
+size 6595

languagecodes.py

@@ -0,0 +1,745 @@
+nllb_language_codes: dict[str, str] = {
+    "Acehnese (Arabic script)": "ace_Arab",
+    "Acehnese (Latin script)": "ace_Latn",
+    "Mesopotamian Arabic": "acm_Arab",
+    "Ta’izzi-Adeni Arabic": "acq_Arab",
+    "Tunisian Arabic": "aeb_Arab",
+    "Afrikaans": "afr_Latn",
+    "South Levantine Arabic": "ajp_Arab",
+    "Akan": "aka_Latn",
+    "Amharic": "amh_Ethi",
+    "North Levantine Arabic": "apc_Arab",
+    "Modern Standard Arabic": "arb_Arab",
+    "Modern Standard Arabic (Romanized)": "arb_Latn",
+    "Najdi Arabic": "ars_Arab",
+    "Moroccan Arabic": "ary_Arab",
+    "Egyptian Arabic": "arz_Arab",
+    "Assamese": "asm_Beng",
+    "Asturian": "ast_Latn",
+    "Awadhi": "awa_Deva",
+    "Central Aymara": "ayr_Latn",
+    "South Azerbaijani": "azb_Arab",
+    "North Azerbaijani": "azj_Latn",
+    "Bashkir": "bak_Cyrl",
+    "Bambara": "bam_Latn",
+    "Balinese": "ban_Latn",
+    "Belarusian": "bel_Cyrl",
+    "Bemba": "bem_Latn",
+    "Bengali": "ben_Beng",
+    "Bhojpuri": "bho_Deva",
+    "Banjar (Arabic script)": "bjn_Arab",
+    "Banjar (Latin script)": "bjn_Latn",
+    "Standard Tibetan": "bod_Tibt",
+    "Bosnian": "bos_Latn",
+    "Buginese": "bug_Latn",
+    "Bulgarian": "bul_Cyrl",
+    "Catalan": "cat_Latn",
+    "Cebuano": "ceb_Latn",
+    "Czech": "ces_Latn",
+    "Chokwe": "cjk_Latn",
+    "Central Kurdish": "ckb_Arab",
+    "Crimean Tatar": "crh_Latn",
+    "Welsh": "cym_Latn",
+    "Danish": "dan_Latn",
+    "German": "deu_Latn",
+    "Southwestern Dinka": "dik_Latn",
+    "Dyula": "dyu_Latn",
+    "Dzongkha": "dzo_Tibt",
+    "Greek": "ell_Grek",
+    "English": "eng_Latn",
+    "Esperanto": "epo_Latn",
+    "Estonian": "est_Latn",
+    "Basque": "eus_Latn",
+    "Ewe": "ewe_Latn",
+    "Faroese": "fao_Latn",
+    "Fijian": "fij_Latn",
+    "Finnish": "fin_Latn",
+    "Fon": "fon_Latn",
+    "French": "fra_Latn",
+    "Friulian": "fur_Latn",
+    "Nigerian Fulfulde": "fuv_Latn",
+    "Scottish Gaelic": "gla_Latn",
+    "Irish": "gle_Latn",
+    "Galician": "glg_Latn",
+    "Guarani": "grn_Latn",
+    "Gujarati": "guj_Gujr",
+    "Haitian Creole": "hat_Latn",
+    "Hausa": "hau_Latn",
+    "Hebrew": "heb_Hebr",
+    "Hindi": "hin_Deva",
+    "Chhattisgarhi": "hne_Deva",
+    "Croatian": "hrv_Latn",
+    "Hungarian": "hun_Latn",
+    "Armenian": "hye_Armn",
+    "Igbo": "ibo_Latn",
+    "Ilocano": "ilo_Latn",
+    "Indonesian": "ind_Latn",
+    "Icelandic": "isl_Latn",
+    "Italian": "ita_Latn",
+    "Javanese": "jav_Latn",
+    "Japanese": "jpn_Jpan",
+    "Kabyle": "kab_Latn",
+    "Jingpho": "kac_Latn",
+    "Kamba": "kam_Latn",
+    "Kannada": "kan_Knda",
+    "Kashmiri (Arabic script)": "kas_Arab",
+    "Kashmiri (Devanagari script)": "kas_Deva",
+    "Georgian": "kat_Geor",
+    "Central Kanuri (Arabic script)": "knc_Arab",
+    "Central Kanuri (Latin script)": "knc_Latn",
+    "Kazakh": "kaz_Cyrl",
+    "Kabiyè": "kbp_Latn",
+    "Kabuverdianu": "kea_Latn",
+    "Khmer": "khm_Khmr",
+    "Kikuyu": "kik_Latn",
+    "Kinyarwanda": "kin_Latn",
+    "Kyrgyz": "kir_Cyrl",
+    "Kimbundu": "kmb_Latn",
+    "Northern Kurdish": "kmr_Latn",
+    "Kikongo": "kon_Latn",
+    "Korean": "kor_Hang",
+    "Lao": "lao_Laoo",
+    "Ligurian": "lij_Latn",
+    "Limburgish": "lim_Latn",
+    "Lingala": "lin_Latn",
+    "Lithuanian": "lit_Latn",
+    "Lombard": "lmo_Latn",
+    "Latgalian": "ltg_Latn",
+    "Luxembourgish": "ltz_Latn",
+    "Luba-Kasai": "lua_Latn",
+    "Ganda": "lug_Latn",
+    "Luo": "luo_Latn",
+    "Mizo": "lus_Latn",
+    "Standard Latvian": "lvs_Latn",
+    "Magahi": "mag_Deva",
+    "Maithili": "mai_Deva",
+    "Malayalam": "mal_Mlym",
+    "Marathi": "mar_Deva",
+    "Minangkabau (Arabic script)": "min_Arab",
+    "Minangkabau (Latin script)": "min_Latn",
+    "Macedonian": "mkd_Cyrl",
+    "Plateau Malagasy": "plt_Latn",
+    "Maltese": "mlt_Latn",
+    "Meitei (Bengali script)": "mni_Beng",
+    "Halh Mongolian": "khk_Cyrl",
+    "Mossi": "mos_Latn",
+    "Maori": "mri_Latn",
+    "Burmese": "mya_Mymr",
+    "Dutch": "nld_Latn",
+    "Norwegian Nynorsk": "nno_Latn",
+    "Norwegian Bokmål": "nob_Latn",
+    "Nepali": "npi_Deva",
+    "Northern Sotho": "nso_Latn",
+    "Nuer": "nus_Latn",
+    "Nyanja": "nya_Latn",
+    "Occitan": "oci_Latn",
+    "West Central Oromo": "gaz_Latn",
+    "Odia": "ory_Orya",
+    "Pangasinan": "pag_Latn",
+    "Eastern Panjabi": "pan_Guru",
+    "Papiamento": "pap_Latn",
+    "Western Persian": "pes_Arab",
+    "Polish": "pol_Latn",
+    "Portuguese": "por_Latn",
+    "Dari": "prs_Arab",
+    "Southern Pashto": "pbt_Arab",
+    "Ayacucho Quechua": "quy_Latn",
+    "Romanian": "ron_Latn",
+    "Rundi": "run_Latn",
+    "Russian": "rus_Cyrl",
+    "Sango": "sag_Latn",
+    "Sanskrit": "san_Deva",
+    "Santali": "sat_Olck",
+    "Sicilian": "scn_Latn",
+    "Shan": "shn_Mymr",
+    "Sinhala": "sin_Sinh",
+    "Slovak": "slk_Latn",
+    "Slovenian": "slv_Latn",
+    "Samoan": "smo_Latn",
+    "Shona": "sna_Latn",
+    "Sindhi": "snd_Arab",
+    "Somali": "som_Latn",
+    "Southern Sotho": "sot_Latn",
+    "Spanish": "spa_Latn",
+    "Tosk Albanian": "als_Latn",
+    "Sardinian": "srd_Latn",
+    "Serbian": "srp_Cyrl",
+    "Swati": "ssw_Latn",
+    "Sundanese": "sun_Latn",
+    "Swedish": "swe_Latn",
+    "Swahili": "swh_Latn",
+    "Silesian": "szl_Latn",
+    "Tamil": "tam_Taml",
+    "Tatar": "tat_Cyrl",
+    "Telugu": "tel_Telu",
+    "Tajik": "tgk_Cyrl",
+    "Tagalog": "tgl_Latn",
+    "Thai": "tha_Thai",
+    "Tigrinya": "tir_Ethi",
+    "Tamasheq (Latin script)": "taq_Latn",
+    "Tamasheq (Tifinagh script)": "taq_Tfng",
+    "Tok Pisin": "tpi_Latn",
+    "Tswana": "tsn_Latn",
+    "Tsonga": "tso_Latn",
+    "Turkmen": "tuk_Latn",
+    "Tumbuka": "tum_Latn",
+    "Turkish": "tur_Latn",
+    "Twi": "twi_Latn",
+    "Central Atlas Tamazight": "tzm_Tfng",
+    "Uyghur": "uig_Arab",
+    "Ukrainian": "ukr_Cyrl",
+    "Umbundu": "umb_Latn",
+    "Urdu": "urd_Arab",
+    "Northern Uzbek": "uzn_Latn",
+    "Venetian": "vec_Latn",
+    "Vietnamese": "vie_Latn",
+    "Waray": "war_Latn",
+    "Wolof": "wol_Latn",
+    "Xhosa": "xho_Latn",
+    "Eastern Yiddish": "ydd_Hebr",
+    "Yoruba": "yor_Latn",
+    "Yue Chinese": "yue_Hant",
+    "Chinese (Simplified)": "zho_Hans",
+    "Chinese (Traditional)": "zho_Hant",
+    "Standard Malay": "zsm_Latn",
+    "Zulu": "zul_Latn",
+}
+mbart_large_languages: dict[str, str] = {
+    'Arabic': 'ar_AR',
+    'Czech': 'cs_CZ',
+    'German': 'de_DE',
+    'English': 'en_XX',
+    'Spanish': 'es_XX',
+    'Estonian': 'et_EE',
+    'Finnish': 'fi_FI',
+    'French': 'fr_XX',
+    'Gujarati': 'gu_IN',
+    'Hindi': 'hi_IN',
+    'Italian': 'it_IT',
+    'Japanese': 'ja_XX',
+    'Kazakh': 'kk_KZ',
+    'Korean': 'ko_KR',
+    'Lithuanian': 'lt_LT',
+    'Latvian': 'lv_LV',
+    'Burmese': 'my_MM',
+    'Nepali': 'ne_NP',
+    'Dutch': 'nl_XX',
+    'Romanian': 'ro_RO',
+    'Russian': 'ru_RU',
+    'Sinhala': 'si_LK',
+    'Turkish': 'tr_TR',
+    'Vietnamese': 'vi_VN',
+    'Chinese': 'zh_CN',
+    'Afrikaans': 'af_ZA',
+    'Azerbaijani': 'az_AZ',
+    'Bengali': 'bn_IN',
+    'Persian': 'fa_IR',
+    'Hebrew': 'he_IL',
+    'Croatian': 'hr_HR',
+    'Indonesian': 'id_ID',
+    'Georgian': 'ka_GE',
+    'Khmer': 'km_KH',
+    'Macedonian': 'mk_MK',
+    'Malayalam': 'ml_IN',
+    'Mongolian': 'mn_MN',
+    'Marathi': 'mr_IN',
+    'Polish': 'pl_PL',
+    'Pashto': 'ps_AF',
+    'Portuguese': 'pt_XX',
+    'Swedish': 'sv_SE',
+    'Swahili': 'sw_KE',
+    'Tamil': 'ta_IN',
+    'Telugu': 'te_IN',
+    'Thai': 'th_TH',
+    'Tagalog': 'tl_XX',
+    'Ukrainian': 'uk_UA',
+    'Urdu': 'ur_PK',
+    'Xhosa': 'xh_ZA',
+    'Galician': 'gl_ES',
+    'Slovene': 'sl_SI'
+}
+# language code system: ISO 639-1 standard, two-letter codes to represent languages
+iso_languages: dict[str, str] = {
+    "Afrikaans": "af",
+    "Albanian": "sq",
+    "Amharic": "am",
+    "Arabic": "ar",
+    "Armenian": "hy",
+    "Azerbaijani": "az",
+    "Basque": "eu",
+    "Belarusian": "be",
+    "Bengali": "bn",
+    "Bosnian": "bs",
+    "Bulgarian": "bg",
+    "Catalan": "ca",
+    "Cebuano": "ceb",
+    "Chinese (Simplified)": "zh-CN",
+    "Chinese (Traditional)": "zh-TW",
+    "Chinese": "zh",
+    "Corsican": "co",
+    "Croatian": "hr",
+    "Czech": "cs",
+    "Danish": "da",
+    "Dutch": "nl",
+    "English": "en",
+    "Esperanto": "eo",
+    "Estonian": "et",
+    "Finnish": "fi",
+    "French": "fr",
+    "Galician": "gl",
+    "Georgian": "ka",
+    "German": "de",
+    "Greek": "el",
+    "Gujarati": "gu",
+    "Haitian Creole": "ht",
+    "Hausa": "ha",
+    "Hawaiian": "haw",
+    "Hebrew": "he",
+    "Hindi": "hi",
+    "Hungarian": "hu",
+    "Icelandic": "is",
+    "Igbo": "ig",
+    "Indonesian": "id",
+    "Irish": "ga",
+    "Italian": "it",
+    "Japanese": "ja",
+    "Javanese": "jv",
+    "Kannada": "kn",
+    "Kazakh": "kk",
+    "Khmer": "km",
+    "Kinyarwanda": "rw",
+    "Korean": "ko",
+    "Kurdish (Kurmanji)": "ku",
+    "Kyrgyz": "ky",
+    "Lao": "lo",
+    "Latin": "la",
+    "Latvian": "lv",
+    "Lithuanian": "lt",
+    "Luxembourgish": "lb",
+    "Macedonian": "mk",
+    "Malagasy": "mg",
+    "Malay": "ms",
+    "Malayalam": "ml",
+    "Maltese": "mt",
+    "Maori": "mi",
+    "Marathi": "mr",
+    "Mongolian": "mn",
+    "Myanmar (Burmese)": "my",
+    "Nepali": "ne",
+    "Norwegian": "no",
+    "Nyanja (Chichewa)": "ny",
+    "Odia (Oriya)": "or",
+    "Pashto": "ps",
+    "Persian": "fa",
+    "Polish": "pl",
+    "Portuguese": "pt",
+    "Punjabi": "pa",
+    "Romanian": "ro",
+    "Russian": "ru",
+    "Samoan": "sm",
+    "Scots Gaelic": "gd",
+    "Serbian": "sr",
+    "Sesotho": "st",
+    "Shona": "sn",
+    "Sindhi": "sd",
+    "Sinhala": "si",
+    "Slovak": "sk",
+    "Slovenian": "sl",
+    "Somali": "so",
+    "Spanish": "es",
+    "Sundanese": "su",
+    "Swahili": "sw",
+    "Swedish": "sv",
+    "Tagalog (Filipino)": "tl",
+    "Tajik": "tg",
+    "Tamil": "ta",
+    "Tatar": "tt",
+    "Telugu": "te",
+    "Thai": "th",
+    "Turkish": "tr",
+    "Turkmen": "tk",
+    "Ukrainian": "uk",
+    "Urdu": "ur",
+    "Uyghur": "ug",
+    "Uzbek": "uz",
+    "Vietnamese": "vi",
+    "Welsh": "cy",
+    "Xhosa": "xh",
+    "Yiddish": "yi",
+    "Yoruba": "yo",
+    "Zulu": "zu"
+}
+
+# language codes dict sorted by language name
+iso_languages_byname: dict[str, tuple[str, str, str]] = {
+    'Abkhazian': ('ab', 'abk', 'abk'),
+    'Afar': ('aa', 'aar', 'aar'),
+    'Afrikaans': ('af', 'afr', 'afr'),
+    'Akan': ('ak', 'aka', 'aka'),
+    'Albanian': ('sq', 'alb', 'sqi'),
+    'Amharic': ('am', 'amh', 'amh'),
+    'Arabic': ('ar', 'ara', 'ara'),
+    'Aragonese': ('an', 'arg', 'arg'),
+    'Armenian': ('hy', 'arm', 'hye'),
+    'Assamese': ('as', 'asm', 'asm'),
+    'Avaric': ('av', 'ava', 'ava'),
+    'Avestan': ('ae', 'ave', 'ave'),
+    'Aymara': ('ay', 'aym', 'aym'),
+    'Azerbaijani': ('az', 'aze', 'aze'),
+    'Bambara': ('bm', 'bam', 'bam'),
+    'Bashkir': ('ba', 'bak', 'bak'),
+    'Basque': ('eu', 'baq', 'eus'),
+    'Belarusian': ('be', 'bel', 'bel'),
+    'Bengali': ('bn', 'ben', 'ben'),
+    'Bislama': ('bi', 'bis', 'bis'),
+    'Bosnian': ('bs', 'bos', 'bos'),
+    'Breton': ('br', 'bre', 'bre'),
+    'Bulgarian': ('bg', 'bul', 'bul'),
+    'Burmese': ('my', 'bur', 'mya'),
+    'Catalan': ('ca', 'cat', 'cat'),
+    'Chamorro': ('ch', 'cha', 'cha'),
+    'Chechen': ('ce', 'che', 'che'),
+    'Chichewa': ('ny', 'nya', 'nya'),
+    'Chinese': ('zh', 'chi', 'zho'),
+    'Church Slavic': ('cu', 'chu', 'chu'),
+    'Chuvash': ('cv', 'chv', 'chv'),
+    'Cornish': ('kw', 'cor', 'cor'),
+    'Corsican': ('co', 'cos', 'cos'),
+    'Cree': ('cr', 'cre', 'cre'),
+    'Croatian': ('hr', 'hrv', 'hrv'),
+    'Czech': ('cs', 'cze', 'ces'),
+    'Danish': ('da', 'dan', 'dan'),
+    'Divehi': ('dv', 'div', 'div'),
+    'Dutch': ('nl', 'dut', 'nld'),
+    'Dzongkha': ('dz', 'dzo', 'dzo'),
+    'English': ('en', 'eng', 'eng'),
+    'Esperanto': ('eo', 'epo', 'epo'),
+    'Estonian': ('et', 'est', 'est'),
+    'Ewe': ('ee', 'ewe', 'ewe'),
+    'Faroese': ('fo', 'fao', 'fao'),
+    'Fijian': ('fj', 'fij', 'fij'),
+    'Finnish': ('fi', 'fin', 'fin'),
+    'French': ('fr', 'fre', 'fra'),
+    'Fulah': ('ff', 'ful', 'ful'),
+    'Galician': ('gl', 'glg', 'glg'),
+    'Ganda': ('lg', 'lug', 'lug'),
+    'Georgian': ('ka', 'geo', 'kat'),
+    'German': ('de', 'ger', 'deu'),
+    'Greek': ('el', 'gre', 'ell'),
+    'Guarani': ('gn', 'grn', 'grn'),
+    'Gujarati': ('gu', 'guj', 'guj'),
+    'Haitian': ('ht', 'hat', 'hat'),
+    'Hausa': ('ha', 'hau', 'hau'),
+    'Hebrew': ('he', 'heb', 'heb'),
+    'Herero': ('hz', 'her', 'her'),
+    'Hindi': ('hi', 'hin', 'hin'),
+    'Hiri Motu': ('ho', 'hmo', 'hmo'),
+    'Hungarian': ('hu', 'hun', 'hun'),
+    'Icelandic': ('is', 'ice', 'isl'),
+    'Ido': ('io', 'ido', 'ido'),
+    'Igbo': ('ig', 'ibo', 'ibo'),
+    'Indonesian': ('id', 'ind', 'ind'),
+    'Interlingua': ('ia', 'ina', 'ina'),
+    'Interlingue': ('ie', 'ile', 'ile'),
+    'Inuktitut': ('iu', 'iku', 'iku'),
+    'Inupiaq': ('ik', 'ipk', 'ipk'),
+    'Irish': ('ga', 'gle', 'gle'),
+    'Italian': ('it', 'ita', 'ita'),
+    'Japanese': ('ja', 'jpn', 'jpn'),
+    'Javanese': ('jv', 'jav', 'jav'),
+    'Kalaallisut': ('kl', 'kal', 'kal'),
+    'Kannada': ('kn', 'kan', 'kan'),
+    'Kanuri': ('kr', 'kau', 'kau'),
+    'Kashmiri': ('ks', 'kas', 'kas'),
+    'Kazakh': ('kk', 'kaz', 'kaz'),
+    'Khmer': ('km', 'khm', 'khm'),
+    'Kikuyu': ('ki', 'kik', 'kik'),
+    'Kinyarwanda': ('rw', 'kin', 'kin'),
+    'Kirghiz': ('ky', 'kir', 'kir'),
+    'Komi': ('kv', 'kom', 'kom'),
+    'Kongo': ('kg', 'kon', 'kon'),
+    'Korean': ('ko', 'kor', 'kor'),
+    'Kuanyama': ('kj', 'kua', 'kua'),
+    'Kurdish': ('ku', 'kur', 'kur'),
+    'Lao': ('lo', 'lao', 'lao'),
+    'Latin': ('la', 'lat', 'lat'),
+    'Latvian': ('lv', 'lav', 'lav'),
+    'Limburgan': ('li', 'lim', 'lim'),
+    'Lingala': ('ln', 'lin', 'lin'),
+    'Lithuanian': ('lt', 'lit', 'lit'),
+    'Luba-Katanga': ('lu', 'lub', 'lub'),
+    'Luxembourgish': ('lb', 'ltz', 'ltz'),
+    'Macedonian': ('mk', 'mac', 'mkd'),
+    'Malagasy': ('mg', 'mlg', 'mlg'),
+    'Malay': ('ms', 'may', 'msa'),
+    'Malayalam': ('ml', 'mal', 'mal'),
+    'Maltese': ('mt', 'mlt', 'mlt'),
+    'Manx': ('gv', 'glv', 'glv'),
+    'Maori': ('mi', 'mao', 'mri'),
+    'Marathi': ('mr', 'mar', 'mar'),
+    'Marshallese': ('mh', 'mah', 'mah'),
+    'Mongolian': ('mn', 'mon', 'mon'),
+    'Nauru': ('na', 'nau', 'nau'),
+    'Navajo': ('nv', 'nav', 'nav'),
+    'Ndonga': ('ng', 'ndo', 'ndo'),
+    'Nepali': ('ne', 'nep', 'nep'),
+    'North Ndebele': ('nd', 'nde', 'nde'),
+    'Northern Sami': ('se', 'sme', 'sme'),
+    'Norwegian': ('no', 'nor', 'nor'),
+    'Norwegian Bokmål': ('nb', 'nob', 'nob'),
+    'Norwegian Nynorsk': ('nn', 'nno', 'nno'),
+    'Occitan': ('oc', 'oci', 'oci'),
+    'Ojibwa': ('oj', 'oji', 'oji'),
+    'Oriya': ('or', 'ori', 'ori'),
+    'Oromo': ('om', 'orm', 'orm'),
+    'Ossetian': ('os', 'oss', 'oss'),
+    'Pali': ('pi', 'pli', 'pli'),
+    'Panjabi': ('pa', 'pan', 'pan'),
+    'Persian': ('fa', 'per', 'fas'),
+    'Polish': ('pl', 'pol', 'pol'),
+    'Portuguese': ('pt', 'por', 'por'),
+    'Pushto': ('ps', 'pus', 'pus'),
+    'Quechua': ('qu', 'que', 'que'),
+    'Romanian': ('ro', 'rum', 'ron'),
+    'Romansh': ('rm', 'roh', 'roh'),
+    'Rundi': ('rn', 'run', 'run'),
+    'Russian': ('ru', 'rus', 'rus'),
+    'Samoan': ('sm', 'smo', 'smo'),
+    'Sango': ('sg', 'sag', 'sag'),
+    'Sanskrit': ('sa', 'san', 'san'),
+    'Sardinian': ('sc', 'srd', 'srd'),
+    'Scottish Gaelic': ('gd', 'gla', 'gla'),
+    'Serbian': ('sr', 'srp', 'srp'),
+    'Shona': ('sn', 'sna', 'sna'),
+    'Sichuan Yi': ('ii', 'iii', 'iii'),
+    'Sindhi': ('sd', 'snd', 'snd'),
+    'Sinhala': ('si', 'sin', 'sin'),
+    'Slovak': ('sk', 'slo', 'slk'),
+    'Slovenian': ('sl', 'slv', 'slv'),
+    'Somali': ('so', 'som', 'som'),
+    'South Ndebele': ('nr', 'nbl', 'nbl'),
+    'Southern Sotho': ('st', 'sot', 'sot'),
+    'Spanish': ('es', 'spa', 'spa'),
+    'Sundanese': ('su', 'sun', 'sun'),
+    'Swahili': ('sw', 'swa', 'swa'),
+    'Swati': ('ss', 'ssw', 'ssw'),
+    'Swedish': ('sv', 'swe', 'swe'),
+    'Tagalog': ('tl', 'tgl', 'tgl'),
+    'Tahitian': ('ty', 'tah', 'tah'),
+    'Tajik': ('tg', 'tgk', 'tgk'),
+    'Tamil': ('ta', 'tam', 'tam'),
+    'Tatar': ('tt', 'tat', 'tat'),
+    'Telugu': ('te', 'tel', 'tel'),
+    'Thai': ('th', 'tha', 'tha'),
+    'Tibetan': ('bo', 'tib', 'bod'),
+    'Tigrinya': ('ti', 'tir', 'tir'),
+    'Tonga': ('to', 'ton', 'ton'),
+    'Tsonga': ('ts', 'tso', 'tso'),
+    'Tswana': ('tn', 'tsn', 'tsn'),
+    'Turkish': ('tr', 'tur', 'tur'),
+    'Turkmen': ('tk', 'tuk', 'tuk'),
+    'Twi': ('tw', 'twi', 'twi'),
+    'Uighur': ('ug', 'uig', 'uig'),
+    'Ukrainian': ('uk', 'ukr', 'ukr'),
+    'Urdu': ('ur', 'urd', 'urd'),
+    'Uzbek': ('uz', 'uzb', 'uzb'),
+    'Venda': ('ve', 'ven', 'ven'),
+    'Vietnamese': ('vi', 'vie', 'vie'),
+    'Volapük': ('vo', 'vol', 'vol'),
+    'Walloon': ('wa', 'wln', 'wln'),
+    'Welsh': ('cy', 'wel', 'cym'),
+    'Western Frisian': ('fy', 'fry', 'fry'),
+    'Wolof': ('wo', 'wol', 'wol'),
+    'Xhosa': ('xh', 'xho', 'xho'),
+    'Yiddish': ('yi', 'yid', 'yid'),
+    'Yoruba': ('yo', 'yor', 'yor'),
+    'Zhuang': ('za', 'zha', 'zha'),
+    'Zulu': ('zu', 'zul', 'zul')
+}
+
+# language codes dict sorted by 2-letter code
+iso_languages_byiso1: dict[str, tuple[str, str, str]] = {
+    'ab': ('Abkhazian', 'abk', 'abk'),
+    'aa': ('Afar', 'aar', 'aar'),
+    'af': ('Afrikaans', 'afr', 'afr'),
+    'ak': ('Akan', 'aka', 'aka'),
+    'sq': ('Albanian', 'alb', 'sqi'),
+    'am': ('Amharic', 'amh', 'amh'),
+    'ar': ('Arabic', 'ara', 'ara'),
+    'an': ('Aragonese', 'arg', 'arg'),
+    'hy': ('Armenian', 'arm', 'hye'),
+    'as': ('Assamese', 'asm', 'asm'),
+    'av': ('Avaric', 'ava', 'ava'),
+    'ae': ('Avestan', 'ave', 'ave'),
+    'ay': ('Aymara', 'aym', 'aym'),
+    'az': ('Azerbaijani', 'aze', 'aze'),
+    'bm': ('Bambara', 'bam', 'bam'),
+    'ba': ('Bashkir', 'bak', 'bak'),
+    'eu': ('Basque', 'baq', 'eus'),
+    'be': ('Belarusian', 'bel', 'bel'),
+    'bn': ('Bengali', 'ben', 'ben'),
+    'bi': ('Bislama', 'bis', 'bis'),
+    'bs': ('Bosnian', 'bos', 'bos'),
+    'br': ('Breton', 'bre', 'bre'),
+    'bg': ('Bulgarian', 'bul', 'bul'),
+    'my': ('Burmese', 'bur', 'mya'),
+    'ca': ('Catalan', 'cat', 'cat'),
+    'ch': ('Chamorro', 'cha', 'cha'),
+    'ce': ('Chechen', 'che', 'che'),
+    'ny': ('Chichewa', 'nya', 'nya'),
+    'zh': ('Chinese', 'chi', 'zho'),
+    'cu': ('Church Slavic', 'chu', 'chu'),
+    'cv': ('Chuvash', 'chv', 'chv'),
+    'kw': ('Cornish', 'cor', 'cor'),
+    'co': ('Corsican', 'cos', 'cos'),
+    'cr': ('Cree', 'cre', 'cre'),
+    'hr': ('Croatian', 'hrv', 'hrv'),
+    'cs': ('Czech', 'cze', 'ces'),
+    'da': ('Danish', 'dan', 'dan'),
+    'dv': ('Divehi', 'div', 'div'),
+    'nl': ('Dutch', 'dut', 'nld'),
+    'dz': ('Dzongkha', 'dzo', 'dzo'),
+    'en': ('English', 'eng', 'eng'),
+    'eo': ('Esperanto', 'epo', 'epo'),
+    'et': ('Estonian', 'est', 'est'),
+    'ee': ('Ewe', 'ewe', 'ewe'),
+    'fo': ('Faroese', 'fao', 'fao'),
+    'fj': ('Fijian', 'fij', 'fij'),
+    'fi': ('Finnish', 'fin', 'fin'),
+    'fr': ('French', 'fre', 'fra'),
+    'ff': ('Fulah', 'ful', 'ful'),
+    'gl': ('Galician', 'glg', 'glg'),
+    'lg': ('Ganda', 'lug', 'lug'),
+    'ka': ('Georgian', 'geo', 'kat'),
+    'de': ('German', 'ger', 'deu'),
+    'el': ('Greek', 'gre', 'ell'),
+    'gn': ('Guarani', 'grn', 'grn'),
+    'gu': ('Gujarati', 'guj', 'guj'),
+    'ht': ('Haitian', 'hat', 'hat'),
+    'ha': ('Hausa', 'hau', 'hau'),
+    'he': ('Hebrew', 'heb', 'heb'),
+    'hz': ('Herero', 'her', 'her'),
+    'hi': ('Hindi', 'hin', 'hin'),
+    'ho': ('Hiri Motu', 'hmo', 'hmo'),
+    'hu': ('Hungarian', 'hun', 'hun'),
+    'is': ('Icelandic', 'ice', 'isl'),
+    'io': ('Ido', 'ido', 'ido'),
+    'ig': ('Igbo', 'ibo', 'ibo'),
+    'id': ('Indonesian', 'ind', 'ind'),
+    'ia': ('Interlingua', 'ina', 'ina'),
+    'ie': ('Interlingue', 'ile', 'ile'),
+    'iu': ('Inuktitut', 'iku', 'iku'),
+    'ik': ('Inupiaq', 'ipk', 'ipk'),
+    'ga': ('Irish', 'gle', 'gle'),
+    'it': ('Italian', 'ita', 'ita'),
+    'ja': ('Japanese', 'jpn', 'jpn'),
+    'jv': ('Javanese', 'jav', 'jav'),
+    'kl': ('Kalaallisut', 'kal', 'kal'),
+    'kn': ('Kannada', 'kan', 'kan'),
+    'kr': ('Kanuri', 'kau', 'kau'),
+    'ks': ('Kashmiri', 'kas', 'kas'),
+    'kk': ('Kazakh', 'kaz', 'kaz'),
+    'km': ('Khmer', 'khm', 'khm'),
+    'ki': ('Kikuyu', 'kik', 'kik'),
+    'rw': ('Kinyarwanda', 'kin', 'kin'),
+    'ky': ('Kirghiz', 'kir', 'kir'),
+    'kv': ('Komi', 'kom', 'kom'),
+    'kg': ('Kongo', 'kon', 'kon'),
+    'ko': ('Korean', 'kor', 'kor'),
+    'kj': ('Kuanyama', 'kua', 'kua'),
+    'ku': ('Kurdish', 'kur', 'kur'),
+    'lo': ('Lao', 'lao', 'lao'),
+    'la': ('Latin', 'lat', 'lat'),
+    'lv': ('Latvian', 'lav', 'lav'),
+    'li': ('Limburgan', 'lim', 'lim'),
+    'ln': ('Lingala', 'lin', 'lin'),
+    'lt': ('Lithuanian', 'lit', 'lit'),
+    'lu': ('Luba-Katanga', 'lub', 'lub'),
+    'lb': ('Luxembourgish', 'ltz', 'ltz'),
+    'mk': ('Macedonian', 'mac', 'mkd'),
+    'mg': ('Malagasy', 'mlg', 'mlg'),
+    'ms': ('Malay', 'may', 'msa'),
+    'ml': ('Malayalam', 'mal', 'mal'),
+    'mt': ('Maltese', 'mlt', 'mlt'),
+    'gv': ('Manx', 'glv', 'glv'),
+    'mi': ('Maori', 'mao', 'mri'),
+    'mr': ('Marathi', 'mar', 'mar'),
+    'mh': ('Marshallese', 'mah', 'mah'),
+    'mn': ('Mongolian', 'mon', 'mon'),
+    'na': ('Nauru', 'nau', 'nau'),
+    'nv': ('Navajo', 'nav', 'nav'),
+    'ng': ('Ndonga', 'ndo', 'ndo'),
+    'ne': ('Nepali', 'nep', 'nep'),
+    'nd': ('North Ndebele', 'nde', 'nde'),
+    'se': ('Northern Sami', 'sme', 'sme'),
+    'no': ('Norwegian', 'nor', 'nor'),
+    'nb': ('Norwegian Bokmål', 'nob', 'nob'),
+    'nn': ('Norwegian Nynorsk', 'nno', 'nno'),
+    'oc': ('Occitan', 'oci', 'oci'),
+    'oj': ('Ojibwa', 'oji', 'oji'),
+    'or': ('Oriya', 'ori', 'ori'),
+    'om': ('Oromo', 'orm', 'orm'),
+    'os': ('Ossetian', 'oss', 'oss'),
+    'pi': ('Pali', 'pli', 'pli'),
+    'pa': ('Panjabi', 'pan', 'pan'),
+    'fa': ('Persian', 'per', 'fas'),
+    'pl': ('Polish', 'pol', 'pol'),
+    'pt': ('Portuguese', 'por', 'por'),
+    'ps': ('Pushto', 'pus', 'pus'),
+    'qu': ('Quechua', 'que', 'que'),
+    'ro': ('Romanian', 'rum', 'ron'),
+    'rm': ('Romansh', 'roh', 'roh'),
+    'rn': ('Rundi', 'run', 'run'),
+    'ru': ('Russian', 'rus', 'rus'),
+    'sm': ('Samoan', 'smo', 'smo'),
+    'sg': ('Sango', 'sag', 'sag'),
+    'sa': ('Sanskrit', 'san', 'san'),
+    'sc': ('Sardinian', 'srd', 'srd'),
+    'gd': ('Scottish Gaelic', 'gla', 'gla'),
+    'sr': ('Serbian', 'srp', 'srp'),
+    'sn': ('Shona', 'sna', 'sna'),
+    'ii': ('Sichuan Yi', 'iii', 'iii'),
+    'sd': ('Sindhi', 'snd', 'snd'),
+    'si': ('Sinhala', 'sin', 'sin'),
+    'sk': ('Slovak', 'slo', 'slk'),
+    'sl': ('Slovenian', 'slv', 'slv'),
+    'so': ('Somali', 'som', 'som'),
+    'nr': ('South Ndebele', 'nbl', 'nbl'),
+    'st': ('Southern Sotho', 'sot', 'sot'),
+    'es': ('Spanish', 'spa', 'spa'),
+    'su': ('Sundanese', 'sun', 'sun'),
+    'sw': ('Swahili', 'swa', 'swa'),
+    'ss': ('Swati', 'ssw', 'ssw'),
+    'sv': ('Swedish', 'swe', 'swe'),
+    'tl': ('Tagalog', 'tgl', 'tgl'),
+    'ty': ('Tahitian', 'tah', 'tah'),
+    'tg': ('Tajik', 'tgk', 'tgk'),
+    'ta': ('Tamil', 'tam', 'tam'),
+    'tt': ('Tatar', 'tat', 'tat'),
+    'te': ('Telugu', 'tel', 'tel'),
+    'th': ('Thai', 'tha', 'tha'),
+    'bo': ('Tibetan', 'tib', 'bod'),
+    'ti': ('Tigrinya', 'tir', 'tir'),
+    'to': ('Tonga', 'ton', 'ton'),
+    'ts': ('Tsonga', 'tso', 'tso'),
+    'tn': ('Tswana', 'tsn', 'tsn'),
+    'tr': ('Turkish', 'tur', 'tur'),
+    'tk': ('Turkmen', 'tuk', 'tuk'),
+    'tw': ('Twi', 'twi', 'twi'),
+    'ug': ('Uighur', 'uig', 'uig'),
+    'uk': ('Ukrainian', 'ukr', 'ukr'),
+    'ur': ('Urdu', 'urd', 'urd'),
+    'uz': ('Uzbek', 'uzb', 'uzb'),
+    've': ('Venda', 'ven', 'ven'),
+    'vi': ('Vietnamese', 'vie', 'vie'),
+    'vo': ('Volapük', 'vol', 'vol'),
+    'wa': ('Walloon', 'wln', 'wln'),
+    'cy': ('Welsh', 'wel', 'cym'),
+    'fy': ('Western Frisian', 'fry', 'fry'),
+    'wo': ('Wolof', 'wol', 'wol'),
+    'xh': ('Xhosa', 'xho', 'xho'),
+    'yi': ('Yiddish', 'yid', 'yid'),
+    'yo': ('Yoruba', 'yor', 'yor'),
+    'za': ('Zhuang', 'zha', 'zha'),
+    'zu': ('Zulu', 'zul', 'zul')
+}