app.py

import gradio as gr
from transformers import pipeline

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

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

# demo = gr.Interface.from_pipeline(pipe)
# demo.launch()

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["microphone"], type="filepath"),
    outputs="text",
    title="Whisper Small Italian",
    description="Realtime demo for Italian speech recognition using a fine-tuned Whisper small model.",
)

iface.launch()