File size: 1,200 Bytes
2bb61b8 |
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 |
# inference.py
from pptx import Presentation
import re
from transformers import pipeline
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 main():
file_path = "path/to/your/powerpoint.pptx" # Specify the path to your PowerPoint file
extracted_text = extract_text_from_pptx(file_path)
cleaned_text = re.sub(r'\s+', ' ', extracted_text)
print(cleaned_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']
print("Predicted Label:", predicted_label)
print(f"Evaluate the topic according to {predicted_label} is: {predicted_probability}")
print(summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False))
if __name__ == "__main__":
main()
|