from transformers import pipeline
import gradio as gr

pipe = pipeline(model="Yilin98/whisper-small-hi")  # change to "your-username/the-name-you-picked"

def transcribe(audio=None, file=None):
    if (audio is None) and (file is None):
        return "No audio provided!"
    elif audio is not None:
        input=audio
    elif file is not None:
        imput=file
    text = pipe(input)["text"]
    return text

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

iface.launch()