app.py

import gradio as gr
from transformers import pipeline
import soundfile as sf

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

def transcribe(audio_file):
    with audio_file as f:
        data, samplerate = sf.read(f.name)
    transcription = asr_model(data, samplerate=samplerate)
    return transcription["text"]

iface = gr.Interface(
    fn=transcribe,
    inputs="audio",
    outputs="text"
)

iface.launch()