from transformers import pipeline
import gradio as gr

pipe = pipeline("automatic-speech-recognition", model="GroupSix/whisper-small-sv")


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


iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(),  # Removed the 'source' and 'type' arguments
    outputs="text",
    title="Whisper Small Swedish",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)

iface.launch()