Spaces:
Running
Running
| import streamlit as st | |
| from transformers import pipeline | |
| from PIL import Image | |
| import pytesseract | |
| import logging | |
| import PyPDF2 | |
| # Setup logging | |
| def setup_logging(): | |
| logging.basicConfig( | |
| level=logging.INFO, | |
| format="%(asctime)s - %(levelname)s - %(message)s", | |
| handlers=[logging.StreamHandler()], | |
| ) | |
| # Text extraction from image | |
| def extract_text_from_image(image): | |
| try: | |
| text = pytesseract.image_to_string(image) | |
| return text | |
| except Exception as e: | |
| logging.error(f"Error during OCR: {e}") | |
| return "Error occurred during text extraction." | |
| # Text extraction from PDF | |
| def extract_text_from_pdf(file): | |
| try: | |
| pdf_reader = PyPDF2.PdfReader(file) | |
| text = "" | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| return text | |
| except Exception as e: | |
| logging.error(f"Error during PDF text extraction: {e}") | |
| return "Error occurred during text extraction." | |
| # Main function | |
| def main(): | |
| setup_logging() | |
| st.title("Lab Report Analyzer") | |
| st.write("Analyze lab reports from images, PDFs, or text and get summaries in English, Hindi, and Urdu.") | |
| # Hugging Face pipelines | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") # Summarization model | |
| translator_hi = pipeline("translation", model="Helsinki-NLP/opus-mt-en-hi") # English to Hindi | |
| translator_ur = pipeline("translation", model="Helsinki-NLP/opus-mt-en-ur") # English to Urdu | |
| # File upload section | |
| uploaded_file = st.file_uploader("Upload a file (Image or PDF):", type=["png", "jpg", "jpeg", "pdf"]) | |
| text_input = st.text_area("Or paste your text here:") | |
| if st.button("Analyze"): | |
| extracted_text = "" | |
| # Extract text based on file type | |
| if uploaded_file: | |
| if uploaded_file.name.endswith(".pdf"): | |
| st.info("Extracting text from PDF...") | |
| extracted_text = extract_text_from_pdf(uploaded_file) | |
| else: | |
| st.info("Extracting text from image...") | |
| image = Image.open(uploaded_file) | |
| extracted_text = extract_text_from_image(image) | |
| elif text_input: | |
| extracted_text = text_input | |
| else: | |
| st.warning("Please upload a file or enter text.") | |
| return | |
| # Display extracted text | |
| st.subheader("Extracted Text") | |
| st.text_area("Extracted Text:", extracted_text, height=200) | |
| # Summarize the text | |
| try: | |
| st.info("Summarizing text...") | |
| summary = summarizer(extracted_text, max_length=150, min_length=30, do_sample=False)[0]['summary_text'] | |
| st.subheader("Summary (English)") | |
| st.write(summary) | |
| except Exception as e: | |
| logging.error(f"Error during summarization: {e}") | |
| st.error("An error occurred during summarization.") | |
| # Translate summary to Hindi | |
| try: | |
| st.info("Translating summary to Hindi...") | |
| summary_hi = translator_hi(summary)[0]['translation_text'] | |
| st.subheader("Summary (Hindi)") | |
| st.write(summary_hi) | |
| except Exception as e: | |
| logging.error(f"Error during Hindi translation: {e}") | |
| st.error("An error occurred during Hindi translation.") | |
| # Translate summary to Urdu | |
| try: | |
| st.info("Translating summary to Urdu...") | |
| summary_ur = translator_ur(summary)[0]['translation_text'] | |
| st.subheader("Summary (Urdu)") | |
| st.write(summary_ur) | |
| except Exception as e: | |
| logging.error(f"Error during Urdu translation: {e}") | |
| st.error("An error occurred during Urdu translation.") | |
| if __name__ == "__main__": | |
| main() | |