Spaces:
Sleeping
Sleeping
| # -*- coding: utf-8 -*- | |
| """ | |
| Created on Mon May 8 00:32:30 2023 | |
| @author: ahmet | |
| """ | |
| import pdfplumber | |
| import gradio as gr | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM | |
| def respond(pdf_file): | |
| pdf_file_name = pdf_file.name | |
| all_text = '' | |
| with pdfplumber.open(pdf_file_name) as pdf: | |
| total_pages = len(pdf.pages) | |
| for idx, pdf_page in enumerate(pdf.pages): | |
| single_page_text = pdf_page.extract_text() | |
| all_text = all_text + '\n' + single_page_text | |
| print(idx/total_pages) | |
| if idx/total_pages >0.2: | |
| break | |
| tokenizer=AutoTokenizer.from_pretrained('Einmalumdiewelt/T5-Base_GNAD') | |
| model=AutoModelForSeq2SeqLM.from_pretrained('Einmalumdiewelt/T5-Base_GNAD', return_dict=True) | |
| inputs=tokenizer.encode("sumarize: " +all_text, return_tensors='pt', max_length=512, truncation=True) | |
| output = model.generate(inputs, min_length=70, max_length=80) | |
| summary=tokenizer.decode(output[0]) | |
| return summary | |
| with gr.Blocks() as demo: | |
| title = """<p><h1 align="center" style="font-size: 36px;">Talk with your document</h1></p>""" | |
| gr.HTML(title) | |
| with gr.Row(): | |
| with gr.Column(): | |
| file_input = gr.File(label="PDF File", type="file") | |
| summarize = gr.Button("Summarize") | |
| text_output = gr.Textbox(label="Summarized text") | |
| summarize.click(fn=respond, inputs=file_input, outputs=text_output) | |
| demo.launch(debug=True) |