Brass-monkey's picture
Update app.py
3243b63
raw
history blame
865 Bytes
import gradio as gr
from PyPDF2 import PdfReader
from transformers import pipeline
def summarize_pdf_content(files):
summarizer = pipeline("summarization", model="stevhliu/my_awesome_billsum_model")
summaries = []
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"
summary = summarizer(text, max_length=50, min_length=10, do_sample=False)[0]['summary_text']
summaries.append(summary)
return summaries
iface = gr.Interface(
fn=summarize_pdf_content,
inputs=gr.UploadButton("Click to Upload a PDF", file_types=["pdf"], file_count="multiple"),
outputs=gr.Textbox(label="Summarized Text"),
title="PDF Summarizer"
)
iface.launch()