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 | |
| 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 split the text into smaller chunks | |
| def split_text(text, chunk_size=1024): | |
| words = text.split() | |
| for i in range(0, len(words), chunk_size): | |
| yield ' '.join(words[i:i + chunk_size]) | |
| # Main processing function | |
| def pdf_to_text(text, PDF, min_length=20): | |
| try: | |
| # Extract text from PDF if no input text provided | |
| if text == "": | |
| text = extract_text(PDF.name) | |
| # Split the text into chunks for summarization | |
| summarized_text = "" | |
| for chunk in split_text(text): | |
| # Tokenize chunked text | |
| inputs = tokenizer([chunk], max_length=1024, return_tensors="pt") | |
| min_length = int(min_length) | |
| # Generate summary for each chunk | |
| 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] | |
| summarized_text += output_text + " " # Append each chunk summary | |
| # Save summarized text to PDF | |
| pdf = FPDF() | |
| pdf.add_page() | |
| pdf.set_font("Times", size=12) | |
| pdf.multi_cell(190, 10, txt=summarized_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=summarized_text, lang='en', slow=False) | |
| tts.save(audio_output_path) | |
| return audio_output_path, summarized_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"), 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() | |