app.py

import whisper
import gradio as gr


model = whisper.load_model('base')


def transcribe(inputs, task):
    if inputs is None:
        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")

    result = model.transcribe(inputs)
    return  result["text"]


interface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["microphone"],type="filepath"),
    outputs="text",
    title="Whisper Large V3: Transcribe Audio",
    description=(
        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
    )
)

interface.launch()