File size: 1,583 Bytes
44e21a6 2bb61b8 12b0ed7 2bb61b8 7de2d0b 2bb61b8 12b0ed7 7de2d0b 12b0ed7 e2d35e8 7de2d0b cf38445 12b0ed7 5fe069a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
from pptx import Presentation
import re
from transformers import pipeline
import subprocess
import gradio as gr
def extract_text_from_pptx(file_path):
presentation = Presentation(file_path)
text = []
for slide_number, slide in enumerate(presentation.slides, start=1):
for shape in slide.shapes:
if hasattr(shape, "text"):
text.append(shape.text)
return "\n".join(text)
def predict_pptx_content(file_path):
extracted_text = extract_text_from_pptx(file_path)
cleaned_text = re.sub(r'\s+', ' ', extracted_text)
classifier = pipeline("text-classification", model="Ahmed235/roberta_classification")
#summarizer = pipeline("summarization", model="Falconsai/text_summarization")
result = classifier(cleaned_text)[0]
predicted_label = result['label']
predicted_probability = result['score']
prediction = {
"Predicted Label": predicted_label,
"Evaluation": f"Evaluate the topic according to {predicted_label} is: {predicted_probability}"
#"Summary": summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False)
}
return prediction
# Define the Gradio interface
iface = gr.Interface(
fn=predict_pptx_content,
inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),
outputs=["text", "text"], # Predicted Label, Evaluation, Summary
live=False, # Change to False for one-time analysis
title="<h1 style='color: lightgreen; text-align: center;'>PPTX Analyzer</h1>",
)
# Deploy the Gradio interface
iface.launch(share=True) |