Update app.py

app.py

@@ -40,7 +40,8 @@ def open_image():
 
 
 
-def transcribe(audio):
+def transcribe(audio_input):
+    sr, audio = audio_input
     # Transcribe the audio and split the string into a list of words
     try:
         transcribed_audio = pipe(audio)["text"]
@@ -85,7 +86,7 @@ with gr.Blocks(title="Interactive Language Learning") as demo:
     """)
     with gr.Row():
         with gr.Column():
-            audio = gr.Audio(sources="microphone", type="filepath", label="Record your answer here")
+            audio = gr.Audio(sources="microphone", type="numpy", label="Record your answer here")
         with gr.Column():
             image = gr.Image(value=open_image(),type="pil", interactive=False)
     with gr.Row():