Update app.py

app.py

@@ -10,6 +10,109 @@ import spaces
 import pytube
 import librosa
 
+# Add the LANGUAGES dictionary
+LANGUAGES = {
+    "en": "eng",
+    "zh": "zho",
+    "de": "deu",
+    "es": "spa",
+    "ru": "rus",
+    "ko": "kor",
+    "fr": "fra",
+    "ja": "jpn",
+    "pt": "por",
+    "tr": "tur",
+    "pl": "pol",
+    "ca": "cat",
+    "nl": "nld",
+    "ar": "ara",
+    "sv": "swe",
+    "it": "ita",
+    "id": "ind",
+    "hi": "hin",
+    "fi": "fin",
+    "vi": "vie",
+    "iw": "heb",
+    "uk": "ukr",
+    "el": "ell",
+    "ms": "msa",
+    "cs": "ces",
+    "ro": "ron",
+    "da": "dan",
+    "hu": "hun",
+    "ta": "tam",
+    "no": "nor",
+    "th": "tha",
+    "ur": "urd",
+    "hr": "hrv",
+    "bg": "bul",
+    "lt": "lit",
+    "la": "lat",
+    "mi": "mri",
+    "ml": "mal",
+    "cy": "cym",
+    "sk": "slk",
+    "te": "tel",
+    "fa": "fas",
+    "lv": "lav",
+    "bn": "ben",
+    "sr": "srp",
+    "az": "aze",
+    "sl": "slv",
+    "kn": "kan",
+    "et": "est",
+    "mk": "mkd",
+    "br": "bre",
+    "eu": "eus",
+    "is": "isl",
+    "hy": "hye",
+    "ne": "nep",
+    "mn": "mon",
+    "bs": "bos",
+    "kk": "kaz",
+    "sq": "sqi",
+    "sw": "swa",
+    "gl": "glg",
+    "mr": "mar",
+    "pa": "pan",
+    "si": "sin",
+    "km": "khm",
+    "sn": "sna",
+    "yo": "yor",
+    "so": "som",
+    "af": "afr",
+    "oc": "oci",
+    "ka": "kat",
+    "be": "bel",
+    "tg": "tgk",
+    "sd": "snd",
+    "gu": "guj",
+    "am": "amh",
+    "yi": "yid",
+    "lo": "lao",
+    "uz": "uzb",
+    "fo": "fao",
+    "ht": "hat",
+    "ps": "pus",
+    "tk": "tuk",
+    "nn": "nno",
+    "mt": "mlt",
+    "sa": "san",
+    "lb": "ltz",
+    "my": "mya",
+    "bo": "bod",
+    "tl": "tgl",
+    "mg": "mlg",
+    "as": "asm",
+    "tt": "tat",
+    "haw": "haw",
+    "ln": "lin",
+    "ha": "hau",
+    "ba": "bak",
+    "jw": "jav",
+    "su": "sun",
+}
+
 def extract_audio(video_path):
     video = mp.VideoFileClip(video_path)
     audio = video.audio
@@ -38,7 +141,9 @@ def generate_subtitles(audio_path):
     return [{"start": 0, "end": len(audio_input) / 16000, "text": transcription[0]}]
 
 def translate_subtitles(subtitles, target_language):
-    translator = GoogleTranslator(source='auto', target=target_language)
+    # Use the LANGUAGES dictionary to get the full language name
+    target_lang_code = next((k for k, v in LANGUAGES.items() if v == target_language), target_language)
+    translator = GoogleTranslator(source='auto', target=target_lang_code)
     translated_subtitles = []
     for segment in subtitles:
         translated_text = translator.translate(segment["text"])
@@ -99,7 +204,7 @@ iface = gr.Interface(
     inputs=[
         gr.Video(label="Upload Video"),
         gr.Textbox(label="YouTube Link"),
-        gr.Dropdown(choices=["es", "fr", "de", "it", "ja", "ko", "zh-CN"], label="Target Language")
+        gr.Dropdown(choices=list(LANGUAGES.values()), label="Target Language")
     ],
     outputs=gr.Video(label="Processed Video"),
     title="Video Subtitle Translator",