trying an asr model with streaming microphone input

app.py

@@ -1,8 +1,21 @@
 import gradio as gr
+from transformers import pipeline
 
+p = pipeline("automatic-speech-recognition", model='openai/whisper-small')
 
-def greet(name):
-    return f"Hello {name}!!"
+def transcribe(audio, state=""):
+    text = p(audio)
+    state += text["text"] + " "
+    return state, state
 
-app_interface = gr.Interface(fn=greet, inputs='text', outputs='text')
-app_interface.launch()
+gr.Interface(
+    fn=transcribe, 
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", streaming=True), 
+        "state"
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    live=True).launch()