app.py

import gradio as gr
import torch

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Predict with test data (first 5 rows)

model_ckpt = "GenzNepal/mt5-summarize-nepali"

device = "cuda" if torch.cuda.is_available() else "cpu"

t5_tokenizer = AutoTokenizer.from_pretrained(model_ckpt)

model = AutoModelForSeq2SeqLM.from_pretrained(model_ckpt).to(device)



def summarize(text):
    inputs = t5_tokenizer(text, return_tensors="pt", max_length=1024, padding= "max_length", truncation=True, add_special_tokens=True)
    generation = model.generate(
      input_ids = inputs['input_ids'].to(device),
      attention_mask=inputs['attention_mask'].to(device),
      num_beams=6,
      num_return_sequences=1,
      no_repeat_ngram_size=2,
      repetition_penalty=1.0,
      min_length=100,
      max_length=250,
      length_penalty=2.0,
      early_stopping=True
    )
    # # Convert id tokens to text
    output = t5_tokenizer.decode(generation[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
    return output


demo = gr.Interface(
    fn=summarize,
    inputs=gr.Textbox(lines=5, max_lines=20, label="Input"),
    outputs="Input"
)

if __name__ == "__main__":
    demo.launch()