app.py

import gradio as gr
from transformers import pipeline

model = pipeline("automatic-speech-recognition")


def transcribe_audio(mic=None, file=None):
    if mic is not None:
        audio = mic
    elif file is not None:
        audio = file
    else:
        return "You must either provide a mic recording or a file"
    transcription = model(audio)["text"]
    return transcription


gr.Interface(
    fn=transcribe_audio,
    inputs=[
        gr.Audio(source="microphone", type="filepath", optional=True),
        gr.Audio(source="upload", type="filepath", optional=True),
    ],
    outputs="text",
).launch()