LANGUAGES = [ ("English", "<|en|>"), ("Chinese", "<|zh|>"), ("German", "<|de|>"), ("Spanish", "<|es|>"), ("Russian", "<|ru|>"), ("Korean", "<|ko|>"), ("French", "<|fr|>"), ("Japanese", "<|ja|>"), ("Portuguese", "<|pt|>"), ("Turkish", "<|tr|>"), ("Polish", "<|pl|>"), ("Catalan", "<|ca|>"), ("Dutch", "<|nl|>"), ("Arabic", "<|ar|>"), ("Swedish", "<|sv|>"), ("Italian", "<|it|>"), ("Indonesian", "<|id|>"), ("Hindi", "<|hi|>"), ("Finnish", "<|fi|>"), ("Vietnamese", "<|vi|>"), ("Hebrew", "<|he|>"), ("Ukrainian", "<|uk|>"), ("Greek", "<|el|>"), ("Malay", "<|ms|>"), ("Czech", "<|cs|>"), ("Romanian", "<|ro|>"), ("Danish", "<|da|>"), ("Hungarian", "<|hu|>"), ("Tamil", "<|ta|>"), ("Norwegian", "<|no|>"), ("Thai", "<|th|>"), ("Urdu", "<|ur|>"), ("Croatian", "<|hr|>"), ("Bulgarian", "<|bg|>"), ("Lithuanian", "<|lt|>"), ("Latin", "<|la|>"), ("Maori", "<|mi|>"), ("Malayalam", "<|ml|>"), ("Welsh", "<|cy|>"), ("Slovak", "<|sk|>"), ("Telugu", "<|te|>"), ("Persian", "<|fa|>"), ("Latvian", "<|lv|>"), ("Bengali", "<|bn|>"), ("Serbian", "<|sr|>"), ("Azerbaijani", "<|az|>"), ("Slovenian", "<|sl|>"), ("Kannada", "<|kn|>"), ("Estonian", "<|et|>"), ("Macedonian", "<|mk|>"), ("Breton", "<|br|>"), ("Basque", "<|eu|>"), ("Icelandic", "<|is|>"), ("Armenian", "<|hy|>"), ("Nepali", "<|ne|>"), ("Mongolian", "<|mn|>"), ("Bosnian", "<|bs|>"), ("Kazakh", "<|kk|>"), ("Albanian", "<|sq|>"), ("Swahili", "<|sw|>"), ("Galician", "<|gl|>"), ("Marathi", "<|mr|>"), ("Punjabi", "<|pa|>"), ("Sinhala", "<|si|>"), ("Khmer", "<|km|>"), ("Shona", "<|sn|>"), ("Yoruba", "<|yo|>"), ("Somali", "<|so|>"), ("Afrikaans", "<|af|>"), ("Occitan", "<|oc|>"), ("Georgian", "<|ka|>"), ("Belarusian", "<|be|>"), ("Tajik", "<|tg|>"), ("Sindhi", "<|sd|>"), ("Gujarati", "<|gu|>"), ("Amharic", "<|am|>"), ("Yiddish", "<|yi|>"), ("Lao", "<|lo|>"), ("Uzbek", "<|uz|>"), ("Faroese", "<|fo|>"), ("Haitian Creole", "<|ht|>"), ("Pashto", "<|ps|>"), ("Turkmen", "<|tk|>"), ("Norwegian Nynorsk", "<|nn|>"), ("Maltese", "<|mt|>"), ("Sanskrit", "<|sa|>"), ("Luxembourgish", "<|lb|>"), ("Burmese", "<|my|>"), ("Tibetan", "<|bo|>"), ("Tagalog", "<|tl|>"), ("Malagasy", "<|mg|>"), ("Assamese", "<|as|>"), ("Tatar", "<|tt|>"), ("Hawaiian", "<|haw|>"), ("Lingala", "<|ln|>"), ("Hausa", "<|ha|>"), ("Bashkir", "<|ba|>"), ("Javanese", "<|jw|>"), ("Sundanese", "<|su|>"), ("Cantonese", "<|yue|>"), ]