utils.py

from transformers import pipeline


pipe = pipeline("text2text-generation", model="google-t5/t5-base", device="cpu")
pipe.model.config.pad_token_id = pipe.tokenizer.eos_token_id 

def generate_lesson_from_transcript(doc_text):
    try:
        generated_text = pipe(doc_text, max_length=100, truncation=True)[0]['generated_text']
        output_path = "/tmp/generated_output.txt" 
        
        with open(output_path, "w") as file:
            file.write(generated_text)
        
        return generated_text, output_path
    
    except Exception as e:
        print(f"Bir hata oluştu: {str(e)}")
        return "Bir hata oluştu", None


def split_text_into_chunks(text, chunk_size=1000):
    words = text.split()
    chunks = []
    for i in range(0, len(words), chunk_size):
        chunk = ' '.join(words[i:i+chunk_size])
        chunks.append(chunk)
    return chunks


def generate_lesson_from_chunks(chunks):
    generated_texts = []
    for chunk in chunks:
        generated_text = pipe(chunk, max_length=500)[0]['generated_text']
        generated_texts.append(generated_text)
    return ' '.join(generated_texts)


def process_large_text(text):
    chunks = split_text_into_chunks(text, chunk_size=1000)
    generated_text = generate_lesson_from_chunks(chunks)
    return generated_text