Update app.py

app.py

@@ -4,10 +4,20 @@ 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")
+query_image = Image.open("./images/" + image + ".jpeg")
+
+with gr.Blocks as demo:
+    with gr.row():
+        gr.Label("Vad är detta? Spela in ditt svar med inspelningsknappen!")
+        input_img = gr.Image(query_image)
 def transcribe(audio):
     text = pipe(audio)["text"]
-    return text
+    returntext = ""
+    if text.lower() != image.lower():
+        returntext = "Du svarade fel, ditt svar var: " + text + ", rätt svar var: " + image
+    else:
+        returntext = "Du hade rätt, svaret var: " + image
+    return returntext
 
 iface = gr.Interface(
     fn=transcribe,