Update app.py

app.py

@@ -1,10 +1,10 @@
 from transformers import pipeline
 import gradio as gr
-import glob
+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"]
-print(glob.glob("./images/"))
-
+image = random.choice(images)
+image = gr.Image("./images/" + image + ".jpeg")
 def transcribe(audio):
     text = pipe(audio)["text"]
     return text
@@ -12,8 +12,6 @@ def transcribe(audio):
 iface = gr.Interface(
     fn=transcribe, 
     inputs=gr.Audio(source="microphone", type="filepath"), 
-    # image = 
-    # image = gr.Image(),
     outputs="text",
     title="Whisper Small Swedish",
     description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",