app.py

import gradio as gr
from transformers import pipeline

# Load once at startup
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

text = """BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.
BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.
BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering).
This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs."""

# Summarize the text. the length here is in tokens
summary = summarizer(text, min_length=10, max_length=100)

# Code 5 - define a function to summarize text
def nlp(input_text):
    summary = summarizer(
        input_text,
        repetition_penalty=5.0,  # Increase this to discourage repetition
        length_penalty=0.3,      # Decrease this to generate longer summaries
        min_length=20, max_length=100
    )
    return summary[0]["summary_text"]

# Code 6 - UI object
ui = gr.Interface(nlp,
    inputs=gr.Textbox(label="Input Text"),
    outputs=gr.Textbox(label="Summary"),
    title="Text Summarizer",
    description="Summarize your text using the BART model.")

# Code 7 - launch UI
ui.launch(share=True)