Update app.py

app.py

@@ -4,7 +4,7 @@ from numpy import random
 from PIL import Image
 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)
+image = random.choice(images)
 
 def transcribe(audio, img):
     text = pipe(audio)["text"]
@@ -20,7 +20,7 @@ def transcribe(audio, img):
 
 iface = gr.Interface(
     fn=transcribe, 
-    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Image("./images/" + random.choice(images) + ".jpeg")], 
+    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Image("./images/" + image + ".jpeg")], 
     outputs="text",
     title="Whisper Small Swedish",
     description="Demo of whisper small ASR fine tuned to swedish. Vad är det på bilden? Spela in ditt svar genom att trycka på inspelningsknappen!",