app.py

from transformers import pipeline
import gradio as gr
from numpy import random 
pipe = pipeline(model="fimster/whisper-small-sv-SE")  # change to "your-username/the-name-you-picked"
images = ["katt", "melon", "hund", "banan"]
image = random.choice(images)
query_image = gr.Image("./images/" + image + ".jpeg")
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",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)


iface.launch()