Spaces:
Sleeping
Sleeping
Upload 2 files
Browse files- app.py +56 -0
- requirements.txt +4 -0
app.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from transformers import pipeline
|
| 3 |
+
from PyPDF2 import PdfReader
|
| 4 |
+
import os
|
| 5 |
+
|
| 6 |
+
# Load a summarization model
|
| 7 |
+
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
| 8 |
+
|
| 9 |
+
# Function to summarize text
|
| 10 |
+
def summarize_text(text, max_length, min_length):
|
| 11 |
+
summary = summarizer(text, max_length=int(max_length), min_length=int(min_length), do_sample=False)
|
| 12 |
+
return summary[0]['summary_text']
|
| 13 |
+
|
| 14 |
+
# Function to summarize uploaded documents
|
| 15 |
+
def summarize_document(file, max_length, min_length):
|
| 16 |
+
# Read the content of the file
|
| 17 |
+
if file.name.endswith(".pdf"):
|
| 18 |
+
reader = PdfReader(file.name)
|
| 19 |
+
text = ""
|
| 20 |
+
for page in reader.pages:
|
| 21 |
+
text += page.extract_text()
|
| 22 |
+
else:
|
| 23 |
+
text = file.read().decode("utf-8")
|
| 24 |
+
|
| 25 |
+
# Summarize the extracted text
|
| 26 |
+
if len(text) > 1024: # Summarizer has input size limitations
|
| 27 |
+
text = text[:1024]
|
| 28 |
+
|
| 29 |
+
summary = summarize_text(text, max_length, min_length)
|
| 30 |
+
return summary
|
| 31 |
+
|
| 32 |
+
# Gradio Interface
|
| 33 |
+
with gr.Blocks() as interface:
|
| 34 |
+
gr.Markdown("# Document Summarizer")
|
| 35 |
+
|
| 36 |
+
with gr.Tab("Text Summarization"):
|
| 37 |
+
input_text = gr.Textbox(lines=10, placeholder="Enter the text to summarize...", label="Input Text")
|
| 38 |
+
max_len = gr.Slider(50, 300, value=130, label="Max Summary Length")
|
| 39 |
+
min_len = gr.Slider(10, 50, value=30, label="Min Summary Length")
|
| 40 |
+
output_text = gr.Textbox(lines=5, label="Summary")
|
| 41 |
+
summarize_button = gr.Button("Summarize")
|
| 42 |
+
|
| 43 |
+
summarize_button.click(summarize_text, [input_text, max_len, min_len], output_text)
|
| 44 |
+
|
| 45 |
+
with gr.Tab("Document Summarization"):
|
| 46 |
+
input_file = gr.File(label="Upload a Document (PDF or TXT)")
|
| 47 |
+
max_len_doc = gr.Slider(50, 300, value=130, label="Max Summary Length")
|
| 48 |
+
min_len_doc = gr.Slider(10, 50, value=30, label="Min Summary Length")
|
| 49 |
+
output_doc = gr.Textbox(lines=5, label="Summary")
|
| 50 |
+
summarize_doc_button = gr.Button("Summarize Document")
|
| 51 |
+
|
| 52 |
+
summarize_doc_button.click(summarize_document, [input_file, max_len_doc, min_len_doc], output_doc)
|
| 53 |
+
|
| 54 |
+
# Launch the app
|
| 55 |
+
if __name__ == "__main__":
|
| 56 |
+
interface.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio
|
| 2 |
+
transformers
|
| 3 |
+
torch
|
| 4 |
+
PyPDF2
|