Update app.py

app.py

@@ -58,7 +58,7 @@ def speech_file_to_array_fn(path, max_seconds=10):
 def inference(audio):
    # read in sound file
     # load dummy dataset and read soundfiles
-    ds = speech_file_to_array_fn(audio)
+    ds = speech_file_to_array_fn(audio.name)
     # infer model
     input_values = processor(
           ds["speech"],