Spaces:
Build error
Build error
| import streamlit as st | |
| import re | |
| import nltk | |
| nltk.download('punkt_tab') # Ensure sentence tokenizers are available. | |
| # Import your summarizer. Replace these paths with your actual model and tokenizer paths. | |
| from summarizer import Summarizer | |
| def clean_text(text): | |
| """ | |
| Cleans the text by removing extra whitespace. | |
| You can expand this function to include additional cleaning as needed. | |
| """ | |
| cleaned = re.sub(r'\s+', ' ', text).strip() | |
| return cleaned | |
| # Initialize your summarizer. Make sure to set the correct paths. | |
| MODEL_PATH = r"server_side_summarize_news" # Replace with your model path. | |
| TOKENIZER_PATH = r"server_side_summarize_news" # Replace with your tokenizer path. | |
| summarizer = Summarizer(MODEL_PATH, TOKENIZER_PATH) | |
| # Set up the Streamlit UI. | |
| st.title("Text Summarizer") | |
| st.write("Enter your text below to generate a summary:") | |
| # Text area for user input. | |
| input_text = st.text_area("Input Text", height=200) | |
| # When the 'Summarize' button is pressed, process the input. | |
| if st.button("Summarize"): | |
| if not input_text.strip(): | |
| st.warning("Please enter some text to summarize.") | |
| else: | |
| # Clean the input text. | |
| cleaned_text = clean_text(input_text) | |
| try: | |
| # Generate the summary using your summarizer. | |
| summary = summarizer.iterative_summarization(cleaned_text) | |
| st.subheader("Summary") | |
| st.write(summary) | |
| except Exception as e: | |
| st.error(f"An error occurred during summarization: {e}") | |