app.py

import torch
import gradio as gr

# Use a pipeline as a high-level helper
from transformers import pipeline

# Use a pipeline as a high-level helper
# Use a pipeline as a high-level helper
from transformers import pipeline

text_summary = pipeline("summarization", model="sshleifer/distilbart-xsum-1-1", torch_dtype=torch.bfloat16)

# model_path=("../Models/models--sshleifer--distilbart-xsum-1-1/snapshots/891968fcbb0e421075cc2c3dfc8da8d4b24d54a4")
# text_summary = pipeline("summarization", model=model_path,
#                 torch_dtype=torch.bfloat16)

"""torch_dtype=torch.bfloat16 this parameter helps in compressing the
model without compromising the performance"""

text="Elon Reeve Musk (/ˈiːlɒn/ EE-lon; born June 28, 1971) is a businessman known for his leadership of Tesla, SpaceX, and X (formerly Twitter). Since 2025, he has been a senior advisor to United States President Donald Trump and the de facto head of the Department of Government Efficiency (DOGE). Musk is the wealthiest person in the world; as of March 2025, Forbes estimates his net worth to be US$345 billion. He was named Time magazine's Person of the Year in 2021."
#print(text_summary(text))

"Gradio actually accepts a function, whatever input we give it gives back to the function"
def summary(input):
    output=text_summary(input)
    return output[0]['summary_text']

gr.close_all()

# demo = gr.Interface(fn=summary, inputs="text", outputs="text")
demo = gr.Interface(fn=summary,
                    inputs=[gr.Textbox(label="Input text to summarize", lines=6)],
                    outputs=[gr.Textbox(label="Summarized text",lines=4)],
                    title="GenAi Text Summarizer",
                    description="This application is used to create the summary of the text")
demo.launch(share=True)