from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
import torch
import gradio as gr


# Step 1: Create the pipeline
# text_summary = pipeline("summarization", model="Falconsai/text_summarization")

text_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")

# Step 2: Load the model and modify its dtype
model = AutoModelForSeq2SeqLM.from_pretrained(
    "sshleifer/distilbart-cnn-12-6", torch_dtype=torch.bfloat16)

# Step 3: Replace the model in the pipeline
text_summary.model = model


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="Abhinav 1: Text Summarizer",
                    description="THIS APPLICATION WILL BE USED TO SUMMARIZE THE TEXT")
demo.launch(share=True)