File size: 2,158 Bytes
98c0f54 18332e8 d6ff263 bbeaa3a 09ca2da 18332e8 ecd8fcb 09ca2da 2bb61b8 c4d5545 2bb61b8 d6ff263 12b0ed7 95d05cb 8cb1867 b246175 d6ff263 18332e8 d6ff263 98c0f54 18332e8 d6ff263 d077b39 8d2b38e d077b39 367a8a1 95d05cb 12b0ed7 fcf7672 8d2b38e d6ff263 bcb2ab6 12b0ed7 2292b28 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
import gradio as gr
from transformers import pipeline
from pptx import Presentation
import re
# Create a text classification pipeline
classifier = pipeline("text-classification", model="Ahmed235/roberta_classification", tokenizer="Ahmed235/roberta_classification")
summarizer = pipeline("summarization", model="Falconsai/text_summarization")
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 limit_text_length(text, max_length=512):
# Truncate or limit the text length
return text[:max_length]
def predict_pptx_content(file_path):
try:
extracted_text = extract_text_from_pptx(file_path)
cleaned_text = re.sub(r'\s+', ' ', extracted_text)
# Limit text length before classification
limited_text = limit_text_length(cleaned_text)
# Perform inference using the pipeline
result = classifier(limited_text)
predicted_label = result[0]['label']
predicted_probability = result[0]['score']
summary = summarizer(extracted_text, max_length=80, min_length=30, do_sample=False)[0]['summary_text']
prediction = {
"text": f"Predicted Label: {predicted_label}",
"text": f"Evaluation: Evaluate the topic according to {predicted_label} is: {predicted_probability}",
"text": f"Summary: {summary}",
}
return prediction
except Exception as e:
# Log the error details
print(f"Error in predict_pptx_content: {e}")
return {"error": str(e)}
# Define the Gradio interface
iface = gr.Interface(
fn=predict_pptx_content,
inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),
outputs=["text", "text", "text"], # Use "text" for all components
live=False,
title="<h1 style='color: lightgreen; text-align: center;'>HackTalk Analyzer</h1>",
)
# Deploy the Gradio interface
iface.launch(share=True)
|