Update app.py

app.py

@@ -23,7 +23,11 @@ def inference(text,model):
 
 gr.Interface(
     inference, 
-    [gr.inputs.Audio(label="Input",type="filepath"),gr.inputs.Dropdown(choices=["xm_transformer_s2ut_800m-es-en-st-asr-bt_h1_2022"], default="xm_transformer_s2ut_800m-es-en-st-asr-bt_h1_2022", type="value", label="model")
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", optional=True, label="Speak here..."),
+        gr.Audio(source="upload", type="filepath", optional=True, label="Upload your audio here..."),
+    ],
+    [gr.inputs.Dropdown(choices=["xm_transformer_s2ut_800m-es-en-st-asr-bt_h1_2022"], default="xm_transformer_s2ut_800m-es-en-st-asr-bt_h1_2022", type="value", label="Model")
 ],
     gr.outputs.Audio(label="Output"),
     article=article,