Update app.py

app.py

@@ -5,14 +5,8 @@ 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)
-# 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("./images/" + image + ".jpeg")
-demo.launch()
-def transcribe(audio):
+def transcribe(audio, img):
     text = pipe(audio)["text"]
     returntext = ""
     if text.lower() != image.lower():
@@ -23,7 +17,7 @@ def transcribe(audio):
 
 iface = gr.Interface(
     fn=transcribe, 
-    inputs=gr.Audio(source="microphone", type="filepath"), 
+    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Image("./images/" + image + ".jpeg")], 
     outputs="text",
     title="Whisper Small Swedish",
     description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",