simple asr no streaming

app.py

@@ -3,19 +3,12 @@ from transformers import pipeline
 
 p = pipeline("automatic-speech-recognition", model='openai/whisper-small')
 
-def transcribe(audio, state=""):
-    text = p(audio)
-    state += text["text"] + " "
-    return state, state
+def transcribe(audio):
+    text = p(audio)["text"]
+    return text
 
 gr.Interface(
     fn=transcribe, 
-    inputs=[
-        gr.Audio(source="microphone", type="filepath", streaming=True), 
-        "state"
-    ],
-    outputs=[
-        "textbox",
-        "state"
-    ],
-    live=True).launch()
+    inputs=gr.Audio(source="microphone", type="filepath"), 
+    outputs="text").launch()
+