direct input

app.py

@@ -29,11 +29,6 @@ formatter = logging.Formatter(
 ch.setFormatter(formatter)
 logger.addHandler(ch)
 
-inputs = [
-    gr.components.Audio(type="filepath", label="Add music audio file"), 
-    gr.inputs.Audio(source="microphone", type="filepath"),
-]
-
 title = "One Model for All Music Understanding Tasks"
 description = "An example of using the [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) model as backbone to conduct multiple music understanding tasks with the universal representation. \n Due the hardware limitation of the machine hosting this demo (2 CPU and 16GB RAM) only the first 4 seconds of audio are used!"
 with open('./README.md', 'r') as f:
@@ -191,7 +186,7 @@ demo = gr.Blocks()
 with demo:
     gr.Interface(
         fn=convert_audio,
-        inputs=inputs,
+        inputs=gr.Audio(source="microphone"),
         outputs=outputs,
         allow_flagging="never",
         title=title,