Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import pipeline | |
| import fitz # PyMuPDF | |
| import docx | |
| import concurrent.futures | |
| # Summarization pipeline | |
| pipe = pipeline("summarization", model="facebook/bart-large-cnn") | |
| def chunk_text(text, chunk_size=512): | |
| # Split the text into smaller chunks | |
| return [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)] | |
| def summarize_chunk(chunk): | |
| return pipe(chunk)[0]['summary_text'] | |
| def extract_text_from_pdf(file): | |
| text = "" | |
| doc = fitz.open(stream=file.read(), filetype="pdf") | |
| for page in doc: | |
| text += page.get_text() | |
| return text | |
| def extract_text_from_docx(file): | |
| doc = docx.Document(file) | |
| return "\n".join([para.text for para in doc.paragraphs]) | |
| def main(): | |
| st.title("Text Summarization App") | |
| input_text = st.text_area("Enter Text (Due to the Free CPU Basic Hardware being used, it takes more time for the output, please keep the prompt minimal)") | |
| uploaded_file = st.file_uploader("Upload a file", type=['pdf', 'txt', 'doc', 'docx']) | |
| if st.button("Summarize"): | |
| if input_text: | |
| chunks = chunk_text(input_text) | |
| with concurrent.futures.ThreadPoolExecutor() as executor: | |
| summaries = list(executor.map(summarize_chunk, chunks)) | |
| st.subheader("Summary") | |
| st.write(' '.join(summaries)) | |
| elif uploaded_file is not None: | |
| if uploaded_file.type == "application/pdf": | |
| file_text = extract_text_from_pdf(uploaded_file) | |
| elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document": | |
| file_text = extract_text_from_docx(uploaded_file) | |
| elif uploaded_file.type == "text/plain": | |
| file_text = str(uploaded_file.read(), "utf-8") | |
| else: | |
| st.error("Unsupported file type") | |
| return | |
| chunks = chunk_text(file_text) | |
| with concurrent.futures.ThreadPoolExecutor() as executor: | |
| summaries = list(executor.map(summarize_chunk, chunks)) | |
| st.subheader("Summary") | |
| st.write(' '.join(summaries)) | |
| if __name__ == "__main__": | |
| main() | |