update source_languages

app.py

@@ -29,105 +29,105 @@ import psutil
 
 whisper_models = ["tiny", "base", "small", "medium", "large-v1", "large-v2"]
 source_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",
+    "English": "English",
+    # "zh": "Chinese",
+    # "de": "German",
+    # "es": "Spanish",
+    # "ru": "Russian",
+    # "ko": "Korean",
+    # "fr": "French",
+    "Japan": "Japanese",
+    # "pt": "Portuguese",
+    # "tr": "Turkish",
+    # "pl": "Polish",
+    # "ca": "Catalan",
+    # "nl": "Dutch",
+    # "ar": "Arabic",
+    # "sv": "Swedish",
+    # "it": "Italian",
+    "Indonesia": "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",
 }
 
 source_language_list = [key[0] for key in source_languages.items()]
@@ -351,7 +351,7 @@ video_in = gr.Video(label="Video file", mirror_webcam=False)
 youtube_url_in = gr.Textbox(label="Youtube url", lines=1, interactive=True)
 df_init = pd.DataFrame(columns=['Start', 'End', 'Speaker', 'Text'])
 memory = psutil.virtual_memory()
-selected_source_lang = gr.Dropdown(choices=source_language_list, type="value", value="en", label="Spoken language in video", interactive=True)
+selected_source_lang = gr.Dropdown(choices=source_language_list, type="value", value="Indonesia", label="Spoken language in video", interactive=True)
 selected_whisper_model = gr.Dropdown(choices=whisper_models, type="value", value="base", label="Selected Whisper model", interactive=True)
 number_speakers = gr.Number(precision=0, value=0, label="Input number of speakers for better results. If value=0, model will automatic find the best number of speakers", interactive=True)
 system_info = gr.Markdown(f"*Memory: {memory.total / (1024 * 1024 * 1024):.2f}GB, used: {memory.percent}%, available: {memory.available / (1024 * 1024 * 1024):.2f}GB*")