try wave

app.py

@@ -7,9 +7,9 @@ def load_audio_to_tensor(filename):
     return wave
 
 def greet(name):
-    load_audio_to_tensor(name)
+    wave = load_audio_to_tensor(name)
     # return "Hello " + str(name[1]) + "!!"
-    return name + 'type'
+    return wave
 
 iface = gr.Interface(fn=greet, inputs="file", outputs="text")
 # iface = gr.Interface(fn=greet, inputs="audio", outputs="text")