Create app.py

app.py

@@ -0,0 +1,136 @@
+from transformers import MarianTokenizer, MarianMTModel
+import streamlit as st
+from PyPDF2 import PdfReader
+import docx
+import os
+
+# Load translation models and tokenizers
+def load_translation_model(src_lang, tgt_lang):
+    model_name = f"Helsinki-NLP/opus-mt-{src_lang}-{tgt_lang}"
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
+    return tokenizer, model
+
+# Initialize models for supported language pairs
+@st.cache_resource
+def initialize_models():
+    return {
+        "en_hi": load_translation_model("en", "hi"),
+        "en_mr": load_translation_model("en", "mr"),
+        "hi_en": load_translation_model("hi", "en"),
+        "mr_en": load_translation_model("mr", "en")
+    }
+
+# Function to extract text from different file types
+def extract_text(file):
+    ext = os.path.splitext(file.name)[1].lower()
+    
+    if ext == ".pdf":
+        reader = PdfReader(file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+        return text
+    
+    elif ext == ".docx":
+        doc = docx.Document(file)
+        text = ""
+        for para in doc.paragraphs:
+            text += para.text + "\n"
+        return text
+    
+    elif ext == ".txt":
+        return file.read().decode("utf-8")
+    
+    else:
+        raise ValueError("Unsupported file format. Please upload PDF, DOCX, or TXT files.")
+
+# Translation function
+def translate_text(text, src_lang, tgt_lang, models):
+    if src_lang == tgt_lang:
+        return text
+        
+    model_key = f"{src_lang}_{tgt_lang}"
+    if model_key not in models:
+        return "Error: Direct translation between Hindi and Marathi is not supported. Please use English as an intermediate language."
+    
+    tokenizer, model = models[model_key]
+    
+    # Split text into manageable chunks (max 512 tokens)
+    sentences = text.split("\n")
+    translated_text = ""
+    
+    for sentence in sentences:
+        if sentence.strip():
+            inputs = tokenizer(sentence, return_tensors="pt", padding=True, truncation=True, max_length=512)
+            translated = model.generate(**inputs)
+            translated_sentence = tokenizer.decode(translated[0], skip_special_tokens=True)
+            translated_text += translated_sentence + "\n"
+    
+    return translated_text
+
+# Function to save text as a file
+def save_text_to_file(text, original_filename, prefix="translated"):
+    output_filename = f"{prefix}_{os.path.basename(original_filename)}.txt"
+    with open(output_filename, "w", encoding="utf-8") as f:
+        f.write(text)
+    return output_filename
+
+# Main processing function
+def process_document(file, source_lang, target_lang, models):
+    try:
+        # Extract text from uploaded file
+        text = extract_text(file)
+        
+        # Translate the text
+        translated_text = translate_text(text, source_lang, target_lang, models)
+        
+        # Save the result (success or error) to a file
+        if translated_text.startswith("Error:"):
+            output_file = save_text_to_file(translated_text, file.name, prefix="error")
+        else:
+            output_file = save_text_to_file(translated_text, file.name)
+        
+        return output_file, translated_text
+    except Exception as e:
+        # Save error message to a file
+        error_message = f"Error: {str(e)}"
+        output_file = save_text_to_file(error_message, file.name, prefix="error")
+        return output_file, error_message
+
+# Streamlit interface
+def main():
+    st.title("Document Translator")
+    st.write("Upload a document (PDF, DOCX, or TXT) and select source and target languages (English, Hindi, Marathi).")
+    
+    # Initialize models
+    models = initialize_models()
+    
+    # File uploader
+    uploaded_file = st.file_uploader("Upload Document", type=["pdf", "docx", "txt"])
+    
+    # Language selection
+    col1, col2 = st.columns(2)
+    with col1:
+        source_lang = st.selectbox("Source Language", ["en", "hi", "mr"], index=0)
+    with col2:
+        target_lang = st.selectbox("Target Language", ["en", "hi", "mr"], index=1)
+    
+    if uploaded_file is not None and st.button("Translate"):
+        with st.spinner("Translating..."):
+            output_file, result_text = process_document(uploaded_file, source_lang, target_lang, models)
+            
+            # Display result
+            st.text_area("Translated Text", result_text, height=300)
+            
+            # Provide download button
+            with open(output_file, "rb") as file:
+                st.download_button(
+                    label="Download Translated Document",
+                    data=file,
+                    file_name=os.path.basename(output_file),
+                    mime="text/plain"
+                )
+
+if __name__ == "__main__":
+    main()