Spaces:
Sleeping
Sleeping
| import torch | |
| import gradio as gr | |
| from transformers import T5ForConditionalGeneration, T5Tokenizer | |
| import fitz | |
| # Load the model and tokenizer | |
| model_path = 'Sibinraj/T5-finetuned-dialogue_sumxx' | |
| model = T5ForConditionalGeneration.from_pretrained(model_path) | |
| tokenizer = T5Tokenizer.from_pretrained(model_path) | |
| def extract_text_from_pdf(pdf_path): | |
| """ | |
| Extracts text from a given PDF file. | |
| Args: | |
| pdf_path (str): Path to the PDF file. | |
| Returns: | |
| str: Extracted text from the PDF. | |
| """ | |
| text = "" | |
| with fitz.open(pdf_path) as doc: | |
| for page in doc: | |
| text += page.get_text() | |
| return text | |
| def summarize_text(text, max_length, show_length): | |
| """ | |
| Summarizes the given text using a T5 model. | |
| Args: | |
| text (str): The text to summarize. | |
| max_length (int): The maximum length of the summary. | |
| show_length (bool): Whether to show the length of the summary. | |
| Returns: | |
| str: The summarized text. | |
| """ | |
| inputs = tokenizer.encode( | |
| "summarize: " + text, | |
| return_tensors='pt', | |
| max_length=512, | |
| truncation=True, | |
| padding='max_length' | |
| ) | |
| summary_ids = model.generate( | |
| inputs, | |
| max_length=max_length + 20, # Allow some buffer | |
| min_length=10, # Set a reasonable minimum length | |
| num_beams=5, | |
| no_repeat_ngram_size=2, | |
| early_stopping=True | |
| ) | |
| summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True) | |
| summary_words = summary.split() | |
| if len(summary_words) > max_length: | |
| summary = ' '.join(summary_words[:max_length]) | |
| elif len(summary_words) < max_length: | |
| additional_tokens = model.generate( | |
| tokenizer.encode(" ".join(summary_words), return_tensors='pt'), | |
| max_length=max_length - len(summary_words) + len(summary_words), | |
| min_length=max_length - len(summary_words) + len(summary_words), | |
| num_beams=5, | |
| no_repeat_ngram_size=2, | |
| early_stopping=True | |
| ) | |
| additional_summary = tokenizer.decode(additional_tokens[0], skip_special_tokens=True) | |
| summary += ' ' + ' '.join(additional_summary.split()[len(summary_words):max_length]) | |
| if show_length: | |
| summary_length = len(summary.split()) | |
| summary = f"{summary}\n\n(Summary length: {summary_length} words)" | |
| return summary | |
| def handle_input(input_type, text, pdf, max_length, show_length): | |
| """ | |
| Handles the user input based on the selected input type. | |
| Args: | |
| input_type (str): The type of input (text or PDF). | |
| text (str): The text input. | |
| pdf (UploadedFile): The uploaded PDF file. | |
| max_length (int): The maximum length of the summary. | |
| show_length (bool): Whether to show the length of the summary. | |
| Returns: | |
| str: The summarized text. | |
| """ | |
| if input_type == 'Text': | |
| return summarize_text(text, max_length, show_length) | |
| elif input_type == 'PDF': | |
| extracted_text = extract_text_from_pdf(pdf.name) | |
| return summarize_text(extracted_text, max_length, show_length) | |
| # Define the Gradio interface | |
| interface = gr.Interface( | |
| fn=handle_input, | |
| inputs=[ | |
| gr.Radio(['Text', 'PDF'], label='Input Type', type='value'), | |
| gr.Textbox(lines=10, placeholder='Enter Text Here...', label='Input Text', visible=True), | |
| gr.File(label='Upload PDF', type='filepath', visible=True), | |
| gr.Slider(minimum=10, maximum=150, step=1, label='Max Length'), | |
| gr.Checkbox(label='Show summary length', value=False) | |
| ], | |
| outputs=gr.Textbox(label='Summarized Text'), | |
| title='Text or PDF Summarizer using T5-finetuned-dialogue_sumxx' | |
| ) | |
| # Launch the Gradio interface | |
| interface.launch() | |