src/E_Summarization.py

from transformers import MBartForConditionalGeneration, MBart50Tokenizer

def summarize_text(text, max_length=150, min_length=30, num_beams=4):
    # Load the model and tokenizer
    model_name = "facebook/mbart-large-50-many-to-many-mmt"
    tokenizer = MBart50Tokenizer.from_pretrained(model_name)
    model = MBartForConditionalGeneration.from_pretrained(model_name)

    # Ensure max_length and min_length are integers
    max_length = int(max_length)
    min_length = int(min_length)
    num_beams = int(num_beams)

    # Tokenize the input text
    inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)

    # Generate the summary
    summary_ids = model.generate(
        inputs["input_ids"],
        max_length=max_length,
        min_length=min_length,
        num_beams=num_beams,
        length_penalty=2.0,
        early_stopping=True
    )

    # Decode the summary
    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)

    return summary


# Simple summarization function
def simple_summarize_text(text):
    from transformers import pipeline

    summarizer = pipeline("summarization", model="Falconsai/text_summarization")
    summary_text = summarizer(text, max_length=50, min_length=30, do_sample=False)[0]['summary_text']
    return summary_text



# Example text to summarize
#user_text = 'Cat o sa mai astept sa imi deblocati cartela ca nu pot vorbi in Spania si toti prietenii mei asteapta sa ii sun de sarbatori. Deci cand rezolvati problema mea cu cartela?'


#model_name = "facebook/mbart-large-cc25"
def example_summarize_text(model_name, text):
      # Model for multi-language summarization
    summary = summarize_text(model_name, text)
    print("Summary:", summary)

#example_summarize_text(model_name, user_text)

#simple_summarize_text(user_text)