constants.py

LANGUAGES = [
    "English",
    "Chinese",
    "German",
    "Spanish",
    "Russian",
    "Korean",
    "French",
    "Japanese",
    "Portuguese",
    "Turkish",
    "Polish",
    "Catalan",
    "Dutch",
    "Arabic",
    "Swedish",
    "Italian",
    "Indonesian",
    "Hindi",
    "Finnish",
    "Vietnamese",
    "Hebrew",
    "Ukrainian",
    "Greek",
    "Malay",
    "Czech",
    "Romanian",
    "Danish",
    "Hungarian",
    "Tamil",
    "Norwegian",
    "Thai",
    "Urdu",
    "Croatian",
    "Bulgarian",
    "Lithuanian",
    "Latin",
    "Maori",
    "Malayalam",
    "Welsh",
    "Slovak",
    "Telugu",
    "Persian",
    "Latvian",
    "Bengali",
    "Serbian",
    "Azerbaijani",
    "Slovenian",
    "Kannada",
    "Estonian",
    "Macedonian",
    "Breton",
    "Basque",
    "Icelandic",
    "Armenian",
    "Nepali",
    "Mongolian",
    "Bosnian",
    "Kazakh",
    "Albanian",
    "Swahili",
    "Galician",
    "Marathi",
    "Punjabi",
    "Sinhala",
    "Khmer",
    "Shona",
    "Yoruba",
    "Somali",
    "Afrikaans",
    "Occitan",
    "Georgian",
    "Belarusian",
    "Tajik",
    "Sindhi",
    "Gujarati",
    "Amharic",
    "Yiddish",
    "Lao",
    "Uzbek",
    "Faroese",
    "Haitian Creole",
    "Pashto",
    "Turkmen",
    "Nynorsk",
    "Maltese",
    "Sanskrit",
    "Luxembourgish",
    "Myanmar",
    "Tibetan",
    "Tagalog",
    "Malagasy",
    "Assamese",
    "Tatar",
    "Hawaiian",
    "Lingala",
    "Hausa",
    "Bashkir",
    "Javanese",
    "Sundanese",
]

WHISPER_MODELS = [
    "",
    "tiny",
    "base",
    "small",
    "medium",
    "large",
]
language_dict = {
    "": "",
    "en": "English",
    "zh": "Chinese",
    "de": "German",
    "es": "Spanish",
    "ru": "Russian",
    "ko": "Korean",
    "fr": "French",
    "ja": "Japanese",
    "pt": "Portuguese",
    "tr": "Turkish",
    "pl": "Polish",
    "ca": "Catalan",
    "nl": "Dutch",
    "ar": "Arabic",
    "sv": "Swedish",
    "it": "Italian",
    "id": "Indonesian",
    "hi": "Hindi",
    "fi": "Finnish",
    "vi": "Vietnamese",
    "he": "Hebrew",
    "uk": "Ukrainian",
    "el": "Greek",
    "ms": "Malay",
    "cs": "Czech",
    "ro": "Romanian",
    "da": "Danish",
    "hu": "Hungarian",
    "ta": "Tamil",
    "no": "Norwegian",
    "th": "Thai",
    "ur": "Urdu",
    "hr": "Croatian",
    "bg": "Bulgarian",
    "lt": "Lithuanian",
    "la": "Latin",
    "mi": "Maori",
    "ml": "Malayalam",
    "cy": "Welsh",
    "sk": "Slovak",
    "te": "Telugu",
    "fa": "Persian",
    "lv": "Latvian",
    "bn": "Bengali",
    "sr": "Serbian",
    "az": "Azerbaijani",
    "sl": "Slovenian",
    "kn": "Kannada",
    "et": "Estonian",
    "mk": "Macedonian",
    "br": "Breton",
    "eu": "Basque",
    "is": "Icelandic",
    "hy": "Armenian",
    "ne": "Nepali",
    "mn": "Mongolian",
    "bs": "Bosnian",
    "kk": "Kazakh",
    "sq": "Albanian",
    "sw": "Swahili",
    "gl": "Galician",
    "mr": "Marathi",
    "pa": "Punjabi",
    "si": "Sinhala",
    "km": "Khmer",
    "sn": "Shona",
    "yo": "Yoruba",
}


all_languages = list(language_dict.keys()) + list(language_dict.values())