upd

app.py

@@ -5,16 +5,16 @@ import whisper
 
 model = whisper.load_model("base.en")
 
-def fun(audio, state=''):
+def fun(audio) : #, state=''):
+  text = model.transcribe(audio)["text"]
+  #state += text + " "
+  return text
+  
+def fun1(audio, state=''):
   text = model.transcribe(audio)["text"]
   state += text + " "
   return state, state
   
-def transcribe(audio, state=""):
-    text = p(audio)["text"]
-    state += text + " "
-    return state, state
-
 # Set the starting state to an empty string
 
 #gr.Interface(
@@ -34,10 +34,10 @@ gr.Interface(
     title = 'Testing Whisper', 
     fn=fun, 
     inputs=[
-        gr.Audio(source="microphone", streaming = True, type="filepath"),
-        "state"
+        gr.Audio(source="microphone",  type="filepath"), #streaming = True,
+       # "state"
     ],
     outputs=[
-        "textbox", "state"
+        "textbox", # "state"
     ],
     live=True).launch()