app.py

import gradio as gr
from transformers import pipeline

qa_model = pipeline("question-answering",'a-ware/bart-squadv2')

def fetch_answer(question, context ):
    return qa_model(question = question, context = context)['answer']

demo = gr.Interface(
    fn=fetch_answer,
    #take input as real time audio and use OPENAPI whisper for S2T
    inputs=[gr.Textbox(lines=2, placeholder="What is age of patient..."),
            gr.Textbox(lines=2, placeholder="The patient is a 71 year old male...")],
    outputs="text",
    examples=[['questiontest1','context1'],['questiontest2','context2']]
)
demo.launch()