reduce input to only audio

app.py

@@ -2,28 +2,17 @@ from transformers import pipeline
 import gradio as gr
 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)
+pipe = pipeline(model="openai/whisper-medium")  # change to "your-username/the-name-you-picked"
 
 def transcribe(audio, img):
     text = pipe(audio)["text"]
-    text = text.replace("!", "")
-    text = text.replace(".", "")
-    text = text.replace(",", "")
-    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
+    return text
 
 iface = gr.Interface(
     fn=transcribe, 
-    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Image("./images/" + image + ".jpeg")], 
+    inputs=[gr.Audio(source="microphone", type="filepath"),], 
     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!",
+    title="Make transcription of audio",
 )