Update app.py

app.py

@@ -1,7 +1,7 @@
 from transformers import pipeline
 import gradio as gr
 
-# Initialize translation pipeline with Hugging Face's multilingual model
+# Initialize translation pipeline
 translator = pipeline("translation", model="facebook/m2m100_418M")
 
 def translate_text(text, src_lang_code, tgt_lang_code):
@@ -20,123 +20,123 @@ def translate_text(text, src_lang_code, tgt_lang_code):
     )
     return result[0]['translation_text']
 
-# Comprehensive language dictionary (ISO 639-1 codes)
+# Language dictionary with native text examples
 LANGUAGES = {
-    "Afrikaans": "af",
-    "Albanian": "sq",
-    "Amharic": "am",
-    "Arabic": "ar",
-    "Armenian": "hy",
-    "Azerbaijani": "az",
-    "Basque": "eu",
-    "Belarusian": "be",
-    "Bengali": "bn",
-    "Bosnian": "bs",
-    "Bulgarian": "bg",
-    "Catalan": "ca",
-    "Cebuano": "ceb",
-    "Chichewa": "ny",
-    "Chinese (Simplified)": "zh",
-    "Chinese (Traditional)": "zh",
-    "Corsican": "co",
-    "Croatian": "hr",
-    "Czech": "cs",
-    "Danish": "da",
-    "Dutch": "nl",
-    "English": "en",
-    "Esperanto": "eo",
-    "Estonian": "et",
-    "Filipino": "tl",
-    "Finnish": "fi",
-    "French": "fr",
-    "Frisian": "fy",
-    "Galician": "gl",
-    "Georgian": "ka",
-    "German": "de",
-    "Greek": "el",
-    "Gujarati": "gu",
-    "Haitian Creole": "ht",
-    "Hausa": "ha",
-    "Hawaiian": "haw",
-    "Hebrew": "he",
-    "Hindi": "hi",
-    "Hmong": "hmn",
-    "Hungarian": "hu",
-    "Icelandic": "is",
-    "Igbo": "ig",
-    "Indonesian": "id",
-    "Irish": "ga",
-    "Italian": "it",
-    "Japanese": "ja",
-    "Javanese": "jv",
-    "Kannada": "kn",
-    "Kazakh": "kk",
-    "Khmer": "km",
-    "Kinyarwanda": "rw",
-    "Korean": "ko",
-    "Kurdish (Kurmanji)": "ku",
-    "Kyrgyz": "ky",
-    "Lao": "lo",
-    "Latin": "la",
-    "Latvian": "lv",
-    "Lithuanian": "lt",
-    "Luxembourgish": "lb",
-    "Macedonian": "mk",
-    "Malagasy": "mg",
-    "Malay": "ms",
-    "Malayalam": "ml",
-    "Maltese": "mt",
-    "Maori": "mi",
-    "Marathi": "mr",
-    "Mongolian": "mn",
-    "Myanmar (Burmese)": "my",
-    "Nepali": "ne",
-    "Norwegian": "no",
-    "Odia (Oriya)": "or",
-    "Pashto": "ps",
-    "Persian": "fa",
-    "Polish": "pl",
-    "Portuguese": "pt",
-    "Punjabi": "pa",
-    "Romanian": "ro",
-    "Russian": "ru",
-    "Samoan": "sm",
-    "Scots Gaelic": "gd",
-    "Serbian": "sr",
-    "Sesotho": "st",
-    "Shona": "sn",
-    "Sindhi": "sd",
-    "Sinhala": "si",
-    "Slovak": "sk",
-    "Slovenian": "sl",
-    "Somali": "so",
-    "Spanish": "es",
-    "Sundanese": "su",
-    "Swahili": "sw",
-    "Swedish": "sv",
-    "Tajik": "tg",
-    "Tamil": "ta",
-    "Tatar": "tt",
-    "Telugu": "te",
-    "Thai": "th",
-    "Turkish": "tr",
-    "Turkmen": "tk",
-    "Ukrainian": "uk",
-    "Urdu": "ur",
-    "Uyghur": "ug",
-    "Uzbek": "uz",
-    "Vietnamese": "vi",
-    "Welsh": "cy",
-    "Xhosa": "xh",
-    "Yiddish": "yi",
-    "Yoruba": "yo",
-    "Zulu": "zu"
+    "Afrikaans - Afrikaans": "af",
+    "Albanian - Shqip": "sq",
+    "Amharic - አማርኛ": "am",
+    "Arabic - العربية": "ar",
+    "Armenian - Հայերեն": "hy",
+    "Azerbaijani - Azərbaycanca": "az",
+    "Basque - Euskara": "eu",
+    "Belarusian - Беларуская": "be",
+    "Bengali - বাংলা": "bn",
+    "Bosnian - Bosanski": "bs",
+    "Bulgarian - Български": "bg",
+    "Catalan - Català": "ca",
+    "Cebuano - Cebuano": "ceb",
+    "Chichewa - Nyanja": "ny",
+    "Chinese Simplified - 中文": "zh",
+    "Chinese Traditional - 中文": "zh",
+    "Corsican - Corsu": "co",
+    "Croatian - Hrvatski": "hr",
+    "Czech - Čeština": "cs",
+    "Danish - Dansk": "da",
+    "Dutch - Nederlands": "nl",
+    "English - English": "en",
+    "Esperanto - Esperanto": "eo",
+    "Estonian - Eesti": "et",
+    "Filipino - Filipino": "tl",
+    "Finnish - Suomi": "fi",
+    "French - Français": "fr",
+    "Frisian - Frysk": "fy",
+    "Galician - Galego": "gl",
+    "Georgian - ქართული": "ka",
+    "German - Deutsch": "de",
+    "Greek - Ελληνικά": "el",
+    "Gujarati - ગુજરાતી": "gu",
+    "Haitian Creole - Kreyòl ayisyen": "ht",
+    "Hausa - Hausa": "ha",
+    "Hawaiian - ʻŌlelo Hawaiʻi": "haw",
+    "Hebrew - עברית": "he",
+    "Hindi - हिन्दी": "hi",
+    "Hmong - Hmong": "hmn",
+    "Hungarian - Magyar": "hu",
+    "Icelandic - Íslenska": "is",
+    "Igbo - Asụsụ Igbo": "ig",
+    "Indonesian - Bahasa Indonesia": "id",
+    "Irish - Gaeilge": "ga",
+    "Italian - Italiano": "it",
+    "Japanese - 日本語": "ja",
+    "Javanese - Basa Jawa": "jv",
+    "Kannada - ಕನ್ನಡ": "kn",
+    "Kazakh - Қазақша": "kk",
+    "Khmer - ភាសាខ្មែរ": "km",
+    "Kinyarwanda - Kinyarwanda": "rw",
+    "Korean - 한국어": "ko",
+    "Kurdish - Kurdî": "ku",
+    "Kyrgyz - Кыргызча": "ky",
+    "Lao - ພາສາລາວ": "lo",
+    "Latin - Latina": "la",
+    "Latvian - Latviešu": "lv",
+    "Lithuanian - Lietuvių": "lt",
+    "Luxembourgish - Lëtzebuergesch": "lb",
+    "Macedonian - Македонски": "mk",
+    "Malagasy - Malagasy": "mg",
+    "Malay - Bahasa Melayu": "ms",
+    "Malayalam - മലയാളം": "ml",
+    "Maltese - Malti": "mt",
+    "Maori - Te Reo Māori": "mi",
+    "Marathi - मराठी": "mr",
+    "Mongolian - Монгол": "mn",
+    "Myanmar - မြန်မာဘာသာ": "my",
+    "Nepali - नेपाली": "ne",
+    "Norwegian - Norsk": "no",
+    "Odia - ଓଡ଼ିଆ": "or",
+    "Pashto - پښتو": "ps",
+    "Persian - فارسی": "fa",
+    "Polish - Polski": "pl",
+    "Portuguese - Português": "pt",
+    "Punjabi - ਪੰਜਾਬੀ": "pa",
+    "Romanian - Română": "ro",
+    "Russian - Русский": "ru",
+    "Samoan - Gagana Samoa": "sm",
+    "Scots Gaelic - Gàidhlig": "gd",
+    "Serbian - Српски": "sr",
+    "Sesotho - Sesotho": "st",
+    "Shona - ChiShona": "sn",
+    "Sindhi - سنڌي": "sd",
+    "Sinhala - සිංහල": "si",
+    "Slovak - Slovenčina": "sk",
+    "Slovenian - Slovenščina": "sl",
+    "Somali - Soomaali": "so",
+    "Spanish - Español": "es",
+    "Sundanese - Basa Sunda": "su",
+    "Swahili - Kiswahili": "sw",
+    "Swedish - Svenska": "sv",
+    "Tajik - Тоҷикӣ": "tg",
+    "Tamil - தமிழ்": "ta",
+    "Tatar - Татарча": "tt",
+    "Telugu - తెలుగు": "te",
+    "Thai - ไทย": "th",
+    "Turkish - Türkçe": "tr",
+    "Turkmen - Türkmençe": "tk",
+    "Ukrainian - Українська": "uk",
+    "Urdu - اردو": "ur",
+    "Uyghur - ئۇيغۇرچە": "ug",
+    "Uzbek - O'zbekcha": "uz",
+    "Vietnamese - Tiếng Việt": "vi",
+    "Welsh - Cymraeg": "cy",
+    "Xhosa - IsiXhosa": "xh",
+    "Yiddish - יידיש": "yi",
+    "Yoruba - Èdè Yorùbá": "yo",
+    "Zulu - IsiZulu": "zu"
 }
 
 # Create sorted lists for dropdowns
 language_names = sorted(LANGUAGES.keys())
-default_src = "English"
-default_tgt = "Spanish"
+default_src = "English - English"
+default_tgt = "Spanish - Español"
 
 # Gradio interface
 with gr.Blocks(title="Universal Translator") as demo:
@@ -169,18 +169,7 @@ with gr.Blocks(title="Universal Translator") as demo:
             )
     
     translate_btn = gr.Button("Translate", variant="primary")
-    translate_btn.click(
-        translate_text,
-        inputs=[
-            input_text,
-            gr.Textbox(visible=False, value=""),  # Source language code (will be set in function)
-            gr.Textbox(visible=False, value="")   # Target language code (will be set in function)
-        ],
-        outputs=output_text,
-        api_name="translate"
-    )
     
-    # Update button click to include language codes
     def translate_wrapper(text, src_lang_name, tgt_lang_name):
         src_code = LANGUAGES[src_lang_name]
         tgt_code = LANGUAGES[tgt_lang_name]
@@ -194,12 +183,12 @@ with gr.Blocks(title="Universal Translator") as demo:
     
     gr.Examples(
         [
-            ["Hello, how are you today?", "English", "French"],
-            ["The weather is beautiful", "English", "German"],
-            ["I love programming with Python", "English", "Spanish"],
-            ["Machine learning is fascinating", "English", "Chinese (Simplified)"],
-            ["こんにちは、元気ですか？", "Japanese", "English"],
-            ["Bonjour, comment allez-vous?", "French", "Russian"]
+            ["Hello, how are you today?", "English - English", "French - Français"],
+            ["The weather is beautiful", "English - English", "German - Deutsch"],
+            ["I love programming with Python", "English - English", "Spanish - Español"],
+            ["Machine learning is fascinating", "English - English", "Chinese Simplified - 中文"],
+            ["こんにちは、元気ですか？", "Japanese - 日本語", "English - English"],
+            ["Bonjour, comment allez-vous?", "French - Français", "Russian - Русский"]
         ],
         inputs=[input_text, src_lang, tgt_lang]
     )
@@ -207,7 +196,7 @@ with gr.Blocks(title="Universal Translator") as demo:
     gr.Markdown("### Supported Languages")
     gr.Markdown(f"- **Total Languages**: {len(language_names)}")
     gr.Markdown("- **Model**: [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M)")
-    gr.Markdown("- **Note**: First translation may take 10-20 seconds (model loading)")
+    gr.Markdown("- **Tip**: Each language shows how it's written in its own script (e.g., Russian - Русский)")
 
 if __name__ == "__main__":
     demo.launch()