app.py

from transformers import pipeline
import gradio as gr

pipe = pipeline(model="Scalable-ML/whisper-small-sv-dropout-6mb-checkpoint-2000")  

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 Small Swedish to English Translator",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model, and Swedish to English translation using a small T5 model",
)

iface.launch()