Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| import nltk | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM | |
| from fpdf import FPDF | |
| from gtts import gTTS | |
| from pdfminer.high_level import extract_text | |
| from docx import Document | |
| from reportlab.lib.pagesizes import letter | |
| from reportlab.pdfgen import canvas | |
| nltk.download('punkt') | |
| # Load the models and tokenizers once, not every time the function is called | |
| tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn") | |
| model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn") | |
| # Function to convert DOCX to PDF using reportlab (UTF-8 compatible) | |
| def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"): | |
| doc = Document(docx_file) | |
| full_text = [] | |
| for para in doc.paragraphs: | |
| full_text.append(para.text) | |
| # Create a PDF and write the extracted text using reportlab | |
| pdf = canvas.Canvas(output_pdf, pagesize=letter) | |
| pdf.setFont("Helvetica", 12) | |
| # Write text line by line | |
| text = pdf.beginText(40, 750) # Start position on the page | |
| for line in full_text: | |
| text.textLine(line) | |
| pdf.drawText(text) | |
| pdf.save() | |
| return output_pdf | |
| # Main processing function | |
| def pdf_to_text(text, PDF, min_length=20): | |
| try: | |
| # Determine whether the input is a PDF or DOCX | |
| file_extension = os.path.splitext(PDF.name)[1].lower() | |
| # If DOCX, first convert it to PDF | |
| if file_extension == '.docx': | |
| pdf_file_path = docx_to_pdf(PDF.name) # Convert DOCX to PDF | |
| text = extract_text(pdf_file_path) # Extract text from the newly created PDF | |
| # If PDF, extract text from it directly | |
| elif file_extension == '.pdf' and text == "": | |
| text = extract_text(PDF.name) | |
| # Tokenize text | |
| inputs = tokenizer([text], max_length=1024, return_tensors="pt") | |
| min_length = int(min_length) | |
| # Generate summary | |
| summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=min_length, max_length=min_length+1000) | |
| output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0] | |
| # Save summarized text to PDF | |
| pdf = FPDF() | |
| pdf.add_page() | |
| pdf.set_font("Times", size=12) | |
| pdf.multi_cell(190, 10, txt=output_text, align='C') | |
| pdf_output_path = "legal.pdf" | |
| pdf.output(pdf_output_path) | |
| # Convert summarized text to audio | |
| audio_output_path = "legal.wav" | |
| tts = gTTS(text=output_text, lang='en', slow=False) | |
| tts.save(audio_output_path) | |
| return audio_output_path, output_text, pdf_output_path | |
| except Exception as e: | |
| return None, f"An error occurred: {str(e)}", None | |
| # Gradio interface | |
| iface = gr.Interface( | |
| fn=pdf_to_text, | |
| inputs=[gr.Textbox(label="Input Text"), gr.File(label="Upload PDF or DOCX"), gr.Slider(minimum=10, maximum=100, step=10, value=20, label="Summary Minimum Length")], | |
| outputs=[gr.Audio(label="Generated Audio"), gr.Textbox(label="Generated Summary"), gr.File(label="Summary PDF")] | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() | |