Brass-monkey's picture
Update app.py
3fcefd6
raw
history blame
965 Bytes
import gradio as gr
from PyPDF2 import PdfReader
from transformers import pipeline
def summarize_and_extract_text(files):
summarizer = pipeline("summarization")
summaries = []
extracted_texts = []
for file in files:
with open(file.name, "rb") as pdf_file:
pdf_reader = PdfReader(pdf_file)
text = ""
for page in pdf_reader.pages:
text += page.extract_text() + "\n"
extracted_texts.append(text)
summary = summarizer(text, max_length=50, min_length=10, do_sample=False)[0]['summary_text']
summaries.append(summary)
return summaries, extracted_texts
iface = gr.Interface(
fn=summarize_and_extract_text,
inputs=gr.UploadButton("Click to Upload a PDF", file_types=["pdf"], file_count="multiple"),
outputs=[gr.Textbox(label="Summarized Text"), gr.Textbox(label="Extracted Text")],
title="PDF Summarizer & Extracted Text"
)
iface.launch()