Project-2

# Project 2
# FalconAI text summarizer first test (small)

import os
import re
import requests
import sys
from num2words import num2words
import pandas as pd
import numpy as np
import openai
from PyPDF2 import PdfReader

from transformers import pipeline

def main():

    # Sample of text to summarize
    Sample = """Model Description:
The Fine-Tuned T5 Small is a variant of the T5 transformer model, designed for the task of text summarization. It is adapted and fine-tuned to generate concise and coherent summaries of input text.

The model, named "t5-small," is pre-trained on a diverse corpus of text data, enabling it to capture essential information and generate meaningful summaries. Fine-tuning is conducted with careful attention to hyperparameter settings, including batch size and learning rate, to ensure optimal performance for text summarization.

During the fine-tuning process, a batch size of 8 is chosen for efficient computation and learning. Additionally, a learning rate of 2e-5 is selected to balance convergence speed and model optimization. This approach guarantees not only rapid learning but also continuous refinement during training.

The fine-tuning dataset consists of a variety of documents and their corresponding human-generated summaries. This diverse dataset allows the model to learn the art of creating summaries that capture the most important information while maintaining coherence and fluency.

The goal of this meticulous training process is to equip the model with the ability to generate high-quality text summaries, making it valuable for a wide range of applications involving document summarization and content condensation.

"""

    # use FalconsAI to get summary
    summarizer = pipeline("summarization", model="Falconsai/text_summarization")
        # Print model and tokenizer for verification
    #print("Model:", summarizer.model)
    #print("Tokenizer:", summarizer.tokenizer)
    
    # Test summarization with the sample text
    #print("Sample Text:", Sample)
    summary = summarizer(Sample, max_length=200, min_length=25, do_sample=False)
    print("Summary:", summary)

if __name__ == "__main__":
    main()