app.py

import gradio as gr
from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-english")

pipe2 = pipeline("summarization", model="facebook/bart-large-cnn")

def launch(input):
    out = pipe(input)
    out2 = pipe2(input)
    return out[0]['audio']

iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text")

iface.launch()