Update app.py

app.py

@@ -43,108 +43,123 @@ headers = {'Authorization': os.environ['DeepL_API_KEY']}
 whisper_models = ["base", "small", "medium", "large", "base.en"]
 
 
+LANGUAGES = {
+    "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",
+    "so": "somali",
+    "af": "afrikaans",
+    "oc": "occitan",
+    "ka": "georgian",
+    "be": "belarusian",
+    "tg": "tajik",
+    "sd": "sindhi",
+    "gu": "gujarati",
+    "am": "amharic",
+    "yi": "yiddish",
+    "lo": "lao",
+    "uz": "uzbek",
+    "fo": "faroese",
+    "ht": "haitian creole",
+    "ps": "pashto",
+    "tk": "turkmen",
+    "nn": "nynorsk",
+    "mt": "maltese",
+    "sa": "sanskrit",
+    "lb": "luxembourgish",
+    "my": "myanmar",
+    "bo": "tibetan",
+    "tl": "tagalog",
+    "mg": "malagasy",
+    "as": "assamese",
+    "tt": "tatar",
+    "haw": "hawaiian",
+    "ln": "lingala",
+    "ha": "hausa",
+    "ba": "bashkir",
+    "jw": "javanese",
+    "su": "sundanese",
+}
+
+# language code lookup by name, with a few language aliases
 source_languages = {
-"Afrikaans":"af",
-"Amharic":"am",
-"Arabic":"ar",
-"Asturian ":"st",
-"Azerbaijani":"az",
-"Bashkir":"ba",
-"Belarusian":"be",
-"Bulgarian":"bg",
-"Bengali":"bn",
-"Breton":"br",
-"Bosnian":"bs",
-"Catalan; Valencian":"ca",
-"Cebuano":"eb",
-"Czech":"cs",
-"Welsh":"cy",
-"Danish":"da",
-"German":"de",
-"Greeek":"el",
-"English":"en",
-"Spanish":"es",
-"Estonian":"et",
-"Persian":"fa",
-"Fulah":"ff",
-"Finnish":"fi",
-"French":"fr",
-"Western Frisian":"fy",
-"Irish":"ga",
-"Gaelic; Scottish Gaelic":"gd",
-"Galician":"gl",
-"Gujarati":"gu",
-"Hausa":"ha",
-"Hebrew":"he",
-"Hindi":"hi",
-"Croatian":"hr",
-"Haitian; Haitian Creole":"ht",
-"Hungarian":"hu",
-"Armenian":"hy",
-"Indonesian":"id",
-"Igbo":"ig",
-"Iloko":"lo",
-"Icelandic":"is",
-"Italian":"it",
-"Japanese":"ja",
-"Javanese":"jv",
-"Georgian":"ka",
-"Kazakh":"kk",
-"Central Khmer":"km",
-"Kannada":"kn",
-"Korean":"ko",
-"Luxembourgish; Letzeburgesch":"lb",
-"Ganda":"lg",
-"Lingala":"ln",
-"Lao":"lo",
-"Lithuanian":"lt",
-"Latvian":"lv",
-"Malagasy":"mg",
-"Macedonian":"mk",
-"Malayalam":"ml",
-"Mongolian":"mn",
-"Marathi":"mr",
-"Malay":"ms",
-"Burmese":"my",
-"Nepali":"ne",
-"Dutch; Flemish":"nl",
-"Norwegian":"no",
-"Northern Sotho":"ns",
-"Occitan (post 1500)":"oc",
-"Oriya":"or",
-"Panjabi; Punjabi":"pa",
-"Polish":"pl",
-"Pushto; Pashto":"ps",
-"Portuguese":"pt",
-"Romanian; Moldavian; Moldovan":"ro",
-"Russian":"ru",
-"Sindhi":"sd",
-"Sinhala; Sinhalese":"si",
-"Slovak":"sk",
-"Slovenian":"sl",
-"Somali":"so",
-"Albanian":"sq",
-"Serbian":"sr",
-"Swati":"ss",
-"Sundanese":"su",
-"Swedish":"sv",
-"Swahili":"sw",
-"Tamil":"ta",
-"Thai":"th",
-"Tagalog":"tl",
-"Tswana":"tn",
-"Turkish":"tr",
-"Ukrainian":"uk",
-"Urdu":"ur",
-"Uzbek":"uz",
-"Vietnamese":"vi",
-"Wolof":"wo",
-"Xhosa":"xh",
-"Yiddish":"yi",
-"Yoruba":"yo",
-"Chinese":"zh",
-"Zulu":"zu",
-"Let the model analyze": "Let the model analyze"
+    **{language: code for code, language in LANGUAGES.items()},
+    "burmese": "my",
+    "valencian": "ca",
+    "flemish": "nl",
+    "haitian": "ht",
+    "letzeburgesch": "lb",
+    "pushto": "ps",
+    "panjabi": "pa",
+    "moldavian": "ro",
+    "moldovan": "ro",
+    "sinhalese": "si",
+    "castilian": "es",
+    "Let the model analyze": "Let the model analyze"
 }
 
 DeepL_language_codes_for_translation = {
@@ -279,7 +294,7 @@ def speech_to_text(video_file_path, selected_source_lang, whisper_model):
 
 def translate_transcriptions(df, selected_translation_lang_2):
     if selected_translation_lang_2 is None:
-            selected_translation_lang_2 = 'English'
+            selected_translation_lang_2 = 'english'
     df.reset_index(inplace=True)
     
     print("start_translation")