from transformers import pipeline
import gradio as gr

pipe = pipeline(model="mukish45/whisper-base-hi")

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 Base Hindi",
    description="Realtime demo for Hindi speech recognition using a fine-tuned Whisper base model.",
)

iface.launch()