Add missing languages to AUDIO_LANGUAGES constant and remove languages not supported by WhisperX

Author: HenestrosaDev

src/utils/constants.py

@@ -6,77 +6,103 @@
     "af": "Afrikaans",
     "am": "Amharic",
     "ar": "Arabic",
-    "hy": "Armenian",
+    "as": "Assamese",
     "az": "Azerbaijan",
-    "eu": "Basque",
+    "ba": "Bashkir",
     "be": "Belarusian",
-    "bn": "Bengali",
     "bg": "Bulgarian",
+    "bn": "Bengali",
+    "bo": "Tibetan",
+    "br": "Breton",
+    "bs": "Bosnian",
     "ca": "Catalan",
-    "zh": "Chinese (China)",
-    "zh_HK": "Chinese (Hong Kong)",
-    "zh_TW": "Chinese (Taiwan)",
-    "hr": "Croatian",
     "cs": "Czech",
+    "cy": "Welsh",
     "da": "Danish",
-    "nl": "Dutch",
+    "de": "German",
+    "el": "Greek",
     "en": "English",
+    "es": "Spanish",
     "et": "Estonian",
+    "eu": "Basque",
     "fa": "Farsi",
-    "fil": "Filipino",
     "fi": "Finnish",
+    "fo": "Faroese",
     "fr": "French",
     "gl": "Galician",
-    "ka": "Georgian",
-    "de": "German",
-    "de_CH": "German (Swiss Standard)",
-    "el": "Greek",
     "gu": "Gujarati",
-    "iw": "Hebrew",
+    "ha": "Hausa",
+    "haw": "Hawaiian",
+    "he": "Hebrew",
     "hi": "Hindi",
+    "hr": "Croatian",
+    "ht": "Haitian",
     "hu": "Hungarian",
-    "is": "Icelandic",
+    "hy": "Armenian",
     "id": "Indonesian",
+    "is": "Icelandic",
     "it": "Italian",
-    "it_CH": "Swiss Italian",
     "ja": "Japanese",
-    "jv": "Javanese",
-    "kn": "Kannada",
+    "jw": "Javanese",
+    "ka": "Georgian",
     "kk": "Kazakh",
     "km": "Khmer",
+    "kn": "Kannada",
     "ko": "Korean",
+    "la": "Latin",
+    "lb": "Luxembourgish",
+    "ln": "Lingala",
     "lo": "Lao",
-    "lv": "Latvian",
     "lt": "Lithuanian",
-    "ms": "Malay",
+    "lv": "Latvian",
+    "mg": "Malagasy",
+    "mi": "Maori",
+    "mk": "Macedonian",
     "ml": "Malayalam",
-    "mt": "Maltese",
-    "mr": "Marathi",
     "mn": "Mongolian",
+    "mr": "Marathi",
+    "ms": "Malay",
+    "mt": "Maltese",
+    "my": "Burmese",
     "ne": "Nepali",
-    "no": "Norwegian",
+    "nl": "Dutch",
     "nn": "Norwegian Nynorsk",
+    "no": "Norwegian",
+    "oc": "Occitan",
+    "pa": "Punjabi",
     "pl": "Polish",
+    "ps": "Pashto",
     "pt": "Português",
-    "pa": "Punjabi",
     "ro": "Romanian",
     "ru": "Russian",
-    "sr": "Serbian",
+    "sa": "Sanskrit",
+    "sd": "Sindhi",
     "si": "Sinhala",
     "sk": "Slovak",
     "sl": "Slovenian",
-    "es": "Spanish",
+    "sn": "Shona",
+    "so": "Somali",
+    "sq": "Albanian",
+    "sr": "Serbian",
     "su": "Sundanese",
-    "sw": "Swahili",
     "sv": "Swedish",
+    "sw": "Swahili",
     "ta": "Tamil",
     "te": "Telugu",
+    "tg": "Tajik",
     "th": "Thai",
+    "tk": "Turkmen",
+    "tl": "Tagalog",
     "tr": "Turkish",
+    "tt": "Tatar",
     "uk": "Ukrainian",
     "ur": "Urdu",
+    "uz": "Uzbek",
     "vi": "Vietnamese",
-    "zu": "Zulu",
+    "yi": "Yiddish",
+    "yo": "Yoruba",
+    "yue": "Chinese (Yue)",
+    "zh": "Chinese",
 }
 
 AUDIO_FILE_EXTENSIONS = [