app.py

import gradio as gr
import time
from transformers import pipeline

transcriber = pipeline('automatic-speech-recognition',model = "openai/whisper-tiny")

def transcribe(audio):
    sr, y = audio
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return transcriber({"sampling_rate": sr, "raw": y})["text"]

demo = gr.Interface(
    transcribe,
    gr.Audio(sources=["microphone"]),
    "text"
    )
demo.launch()