lang_list.py

# Language dict
language_code_to_name = {
    "afr": "Afrikaans",
    "amh": "Amharic",
    "arb": "Modern Standard Arabic",
    "ary": "Moroccan Arabic",
    "arz": "Egyptian Arabic",
    "asm": "Assamese",
    "ast": "Asturian",
    "azj": "North Azerbaijani",
    "bel": "Belarusian",
    "ben": "Bengali",
    "bos": "Bosnian",
    "bul": "Bulgarian",
    "cat": "Catalan",
    "ceb": "Cebuano",
    "ces": "Czech",
    "ckb": "Central Kurdish",
    "cmn": "Mandarin Chinese",
    "cym": "Welsh",
    "dan": "Danish",
    "deu": "German",
    "ell": "Greek",
    "eng": "English",
    "est": "Estonian",
    "eus": "Basque",
    "fin": "Finnish",
    "fra": "French",
    "gaz": "West Central Oromo",
    "gle": "Irish",
    "glg": "Galician",
    "guj": "Gujarati",
    "heb": "Hebrew",
    "hin": "Hindi",
    "hrv": "Croatian",
    "hun": "Hungarian",
    "hye": "Armenian",
    "ibo": "Igbo",
    "ind": "Indonesian",
    "isl": "Icelandic",
    "ita": "Italian",
    "jav": "Javanese",
    "jpn": "Japanese",
    "kam": "Kamba",
    "kan": "Kannada",
    "kat": "Georgian",
    "kaz": "Kazakh",
    "kea": "Kabuverdianu",
    "khk": "Halh Mongolian",
    "khm": "Khmer",
    "kir": "Kyrgyz",
    "kor": "Korean",
    "lao": "Lao",
    "lit": "Lithuanian",
    "ltz": "Luxembourgish",
    "lug": "Ganda",
    "luo": "Luo",
    "lvs": "Standard Latvian",
    "mai": "Maithili",
    "mal": "Malayalam",
    "mar": "Marathi",
    "mkd": "Macedonian",
    "mlt": "Maltese",
    "mni": "Meitei",
    "mya": "Burmese",
    "nld": "Dutch",
    "nno": "Norwegian Nynorsk",
    "nob": "Norwegian Bokm\u00e5l",
    "npi": "Nepali",
    "nya": "Nyanja",
    "oci": "Occitan",
    "ory": "Odia",
    "pan": "Punjabi",
    "pbt": "Southern Pashto",
    "pes": "Western Persian",
    "pol": "Polish",
    "por": "Portuguese",
    "ron": "Romanian",
    "rus": "Russian",
    "slk": "Slovak",
    "slv": "Slovenian",
    "sna": "Shona",
    "snd": "Sindhi",
    "som": "Somali",
    "spa": "Spanish",
    "srp": "Serbian",
    "swe": "Swedish",
    "swh": "Swahili",
    "tam": "Tamil",
    "tel": "Telugu",
    "tgk": "Tajik",
    "tgl": "Tagalog",
    "tha": "Thai",
    "tur": "Turkish",
    "ukr": "Ukrainian",
    "urd": "Urdu",
    "uzn": "Northern Uzbek",
    "vie": "Vietnamese",
    "xho": "Xhosa",
    "yor": "Yoruba",
    "yue": "Cantonese",
    "zlm": "Colloquial Malay",
    "zsm": "Standard Malay",
    "zul": "Zulu",
}
LANGUAGE_NAME_TO_CODE = {v: k for k, v in language_code_to_name.items()}

# Source langs: S2ST / S2TT / ASR don't need source lang
# T2TT / T2ST use this
text_source_language_codes = [
    "hin",
    "pan",
    "eng",
]
TEXT_SOURCE_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in text_source_language_codes])

# Target langs:
# S2ST / T2ST
s2st_target_language_codes = [
    "eng",
    "arb",
    "ben",
    "cat",
    "ces",
    "cmn",
    "cym",
    "dan",
    "deu",
    "est",
    "fin",
    "fra",
    "hin",
    "ind",
    "ita",
    "jpn",
    "kor",
    "mlt",
    "nld",
    "pes",
    "pol",
    "por",
    "ron",
    "rus",
    "slk",
    "spa",
    "swe",
    "swh",
    "tel",
    "tgl",
    "tha",
    "tur",
    "ukr",
    "urd",
    "uzn",
    "vie",
]
S2ST_TARGET_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in s2st_target_language_codes])
T2ST_TARGET_LANGUAGE_NAMES = S2ST_TARGET_LANGUAGE_NAMES

# S2TT / T2TT / ASR
S2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES
T2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES
ASR_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES