app.py

import gradio as gr
from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small")


def process_input(audio):
    transcription = pipe(audio)["text"]
    return transcription


interface = gr.Interface(
    fn=process_input,
    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
    outputs="text",
    title="testing for data aug",
)

interface.launch()