Update app.py

app.py

@@ -1,154 +1,52 @@
 import gradio as gr
 from transformers import pipeline
+import json
 
-# Initialize the translation pipeline with the T5 model
-text_translator = pipeline("translation_en_to_xx", model="facebook/m2m100_418M")
+# Initialize the translation pipeline with the specific model
+text_translator = pipeline("translation", model="facebook/nllb-200-distilled-600M")
 
-# Dictionary mapping destination languages to their Hugging Face model codes
-language_mapping = {
-    "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-TW",
-    "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",
-    "Tagalog (Filipino)": "tl",
-    "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"
-}
+# Load the JSON table containing language mappings
+with open('language.json') as f:
+    language_data = json.load(f)
 
-def translate_text(text, src_lang, tgt_lang):
+def get_flores_200_code(language):
     """
-    Translates text from source language to target language using the T5 model.
-    
+    Retrieves the FLORES-200 code for a given language from the loaded JSON data.
+
+    Args:
+        language (str): The name of the language.
+
+    Returns:
+        str: The FLORES-200 code for the language, or None if not found.
+    """
+    for code in language_data:
+        if code['Language'] == language:
+            return code['FLORES-200 code']
+    return None
+
+def translate_text(text, destination_language):
+    """
+    Translates text from English to the selected destination language using the T5 model.
+
     Args:
         text (str): The text to translate.
-        src_lang (str): Source language code.
-        tgt_lang (str): Target language code.
-    
+        destination_language (str): The target language for translation.
+
     Returns:
-        str: The translated text or an error message.
+        str: The translated text.
     """
-    src_code = language_mapping.get(src_lang)
-    tgt_code = language_mapping.get(tgt_lang)
-    
-    if not src_code or not tgt_code:
-        return "Unsupported language selected. Please choose valid source and target languages."
+    dest_code = get_flores_200_code(destination_language)
+
+    if not dest_code:
+        return "Unsupported language selected. Please choose a valid language."
 
     try:
         # Perform translation using T5 model pipeline
         translation = text_translator(text,
-                                      src=src_code,
-                                      tgt=tgt_code)
+                                      src_lang="eng_Latn",
+                                      tgt_lang=dest_code)
         translated_text = translation[0]["translation_text"]
-        
-        # Optionally return confidence score
-        score = translation[0].get("score")
-        if score:
-            return f"Translation: {translated_text}\nConfidence Score: {score:.2f}"
-        else:
-            return translated_text
+        return translated_text
     except Exception as e:
         return f"Translation error: {str(e)}"
 
@@ -157,14 +55,13 @@ def main():
     interface = gr.Interface(
         fn=translate_text,
         inputs=[
-            gr.Textbox(label="Input text to translate", lines=6, placeholder="Enter text in source language..."),
-            gr.Dropdown(list(language_mapping.keys()), label="Select source language", default="English"),
-            gr.Dropdown(list(language_mapping.keys()), label="Select destination language")
+            gr.Textbox(label="Input text to translate", lines=6, placeholder="Enter text in English..."),
+            gr.Dropdown([code['Language'] for code in language_data], label="Select destination language")
         ],
         outputs=[gr.Textbox(label="Translated text", lines=4)],
         title="Multi-Language Translator",
-        description="Translate text between multiple languages using the T5 model. Select the source and target languages from the dropdown menus and enter the text to translate.",
-        theme="default",  # Adjusted theme to the correct value
+        description="Translate English text to multiple languages using the T5 model. Select the target language from the dropdown menu and enter the text to translate.",
+        theme=gr.themes.Soft(),
         live=True  # Enable live updates
     )