app.py

import gradio as gr
from transformers import pipeline

# Update this to your actual model name
pipe = pipeline(model="baaabaei/whisper-fa") 

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

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

iface.launch()