languagecodes.py

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 = {
    '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 = {
    "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"
}