Return text and state output

app.py

@@ -7,13 +7,15 @@ model = WhisperModel(model_size, device="cpu", compute_type="int8")
 
 
 def transcribe(audio, state=""):
+    print(audio)
     segments, info = model.transcribe(audio, beam_size=5)
 
     print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
 
     for segment in segments:
         print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
-        state += segment.text + " "
+        if segment.text.lower() != "you":
+            state += segment.text + " "
 
     return state, state