from transformers import pipeline
import gradio as gr

pipe = pipeline(model="Nikolajvestergaard/Japanese_Fine_Tuned_Whisper_Model")

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

iface = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source="microphone", type="filepath"), 
    outputs="text",
    title="Tiny Whisper Model Fine-Tuned on Japanese",
    description="Real-time demo for Japanese speech recognition. Using a fine-tuned tiny Whisper model, trained on the Common Voice dataset.",
)

iface.launch()