import gradio as gr
import torch
from tqdm import tqdm
from transformers import PegasusForConditionalGeneration
from tokenizers_pegasus import PegasusTokenizer

MODEL_NAME = "csebuetnlp/mT5_multilingual_XLSum"

summarizer = PegasusForConditionalGeneration.from_pretrained(MODEL_NAME)
tokenizer = PegasusTokenizer.from_pretrained(MODEL_NAME)

def summarize(text):
    inputs = tokenizer(text, max_length=1024, return_tensors="pt")

    # Generate Summary
    summary_ids = summarizer.generate(inputs["input_ids"])
    return tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

demo = gr.Blocks(title="⭐ Summ4rizer ⭐")
demo.encrypt = False

with demo:
    gr.Markdown(f'''
                <div>
                <h1 style='text-align: center'>Text Summarizer</h1>
                </div>
                <div>
                Using summarization Model from <a href='https://huggingface.co/{MODEL_NAME}' target='_blank'><b>{MODEL_NAME}</b></a>.
                </div>
                ''')
    text = gr.Textbox(label="Text here !!", lines=1, interactive=True)
    summarize_btn = gr.Button("Let's Summarize",)
    summarization = gr.Textbox()
    html_output = gr.Markdown()
    summarize_btn.click(summarize, [text], outputs=[html_output, summarization])

demo.launch()