from transformers import pipeline
import gradio as gr

pipe = pipeline(model="pierrelf/whisper-small-sv")


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


iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["upload", "microphone"], type="filepath"),
    outputs=gr.Text(label="Model output"),
    title="Whisper Swedish",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)


iface.launch(
    server_name="0.0.0.0",
    share=False,
)