I have some issues when trying a python code on choregraph

I'm trying to launch this choregraph app (which is not mine) and I got some issue.I'm following the steps from github:https://github.com/conema/Choregraphe-GA?tab=readme-ov-file, I already configured the server and it works well but when I launch the app I have the error below.

Basically, this apps is supposed to make your robot to act like google assistant.

The 'speech recognition' box works well but leads directly to 'error' box after entering the 'GA' box and I really don't understand why.

I put the GA code and some images.

(I'm new on using choregraph but I really need to make this app works). I need help please.

[enter image description here](https://i.stack.imgur.com/mWYXM.png)

import waveimport timeimport socketimport reimport jsonimport sysimport threadingfrom subprocess import Popen, PIPEfrom threading import Threadfrom Queue import Queue, Empty# TCP clientTCP_IP = '127.0.0.1'TCP_PORT = 4000BUFFER_SIZE = 512# GA answersEOU = "END_OF_UTTERANCE"DFO = "DIALOG_FOLLOW_ON"# Recording comcommand = ['arecord','--format', 'S16_LE','--rate', '16000','--file-type', 'raw']ON_POSIX = 'posix' in sys.builtin_module_namesdef enqueue_output(out, queue):    t = threading.currentThread()    for line in iter(out.readline, b''):        if getattr(t, "stop_t", False):            # Stop thread            break        queue.put(line)    out.close()def connect_ga():    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)    s.connect((TCP_IP, TCP_PORT))    return sdef start_recording():    p = Popen(command, stdout=PIPE, bufsize=1, close_fds=ON_POSIX)    q = Queue()    t = Thread(target=enqueue_output, args=(p.stdout, q))    t.daemon = True    t.start()    return q, tdef remove_emoji(text):    emoji_pattern = re.compile("["        u"\U0001F600-\U0001F64F"  # emoticons        u"\U0001F300-\U0001F5FF"  # symbols & pictographs        u"\U0001F680-\U0001F6FF"  # transport & map symbols        u"\U0001F1E0-\U0001F1FF"  # flags (iOS)"]+", flags=re.UNICODE)    return emoji_pattern.sub(r'', text)class MyClass(GeneratedClass):    def __init__(self):        GeneratedClass.__init__(self)        self.tts = ALProxy('ALTextToSpeech')        self.soundPeak = False    def onLoad(self):        #put initialization code here        pass    def onUnload(self):        #put clean-up code here        self.s.close()        self.t.stop_t = True        self.t.join()        pass    def onInput_audioTrigger(self):        self.soundPeak = True    def start_zora(self):        self.isEOU = False        self.eu = ""        self.q, self.t = start_recording()        self.logger.info("Recording...")        self.s = connect_ga()        self.logger.info("Connected to GA")        self.onListening()    def onInput_onStart(self):        while not self.soundPeak:            pass        self.start_zora()        #audioList = []        while True:            if(not self.isEOU):                #Send audio                try:                    #Get mic data from thread                    data = self.q.get_nowait()                except Empty:                    #If we have no new data, try again                    pass                else:                    #We have data, send it                    #audioList.append(data)                    self.s.send(data)                    self.eu += self.s.recv(BUFFER_SIZE)                if (self.eu is None):                    self.logger.info("Wrong answer from server")                    break                if("0END_OF_UTTERANCE" in self.eu):                    self.isEOU = True                    self.logger.info("END_OF_UTTERANCE")                    while True:                        self.eu += self.s.recv(BUFFER_SIZE)                        #No more data from server                        if("STOP_JSON" in self.eu):                            break                    self.logger.info("finished receiving")                    #Stop thread and wait for exit                    self.t.stop_t = True                    self.t.join()                    self.logger.info("finished recording")            else:                #Analyse answer from google'''                #[DEBUG] write audio                file = wave.open('c:Users/dongm/OneDrive/Bureau/Nao/GA-Server/test/whoisobama.wav', 'wb')                file.setnchannels(1)                file.setframerate(16000)                file.setsampwidth(2)                file.writeframes(b''.join(audioList))                file.close()'''                self.onUnderstood()                data = re.search('START_JSON(.*)STOP_JSON', self.eu)                if data:                    response = json.loads(data.group(1))                    del self.eu                    if "text" in response:                        #We have a text answer from GA                        speach = remove_emoji(response["text"])                        speach = speach.encode('utf-8')                        speach = re.sub(r'\.\n.*\n*\( +.+\)\.*', '', speach) #remove link from supplemental display text                        speach = re.sub(r'-{3}', '', speach) #remove ---                        speach = re.sub(r'\(http.*\)', '', speach) #remove \\nWikipedia (http...)                        speach = re.sub(r'\\n.*', '', speach) #remove \\nWikipedia(http....)                        transcript = unicode(response["transcript"]) #the input audio transcript                        microphone_mode = str(response["microphone_mode"]) #CLOSE_MICROPHONE or DIALOG_FOLLOW_ON                        conversation_state = response["conversation_state"] #state information for the subsequent audio                        #self.logger.info(speach)                        self.tts.say(speach)                        self.s.close()                        self.goReco()                        if microphone_mode != DFO:                            #If GA dont't want an answer from the user                            self.soundPeak = False                            while not self.soundPeak:                                pass                        self.start_zora()                    else:                        self.logger.info("Error/No answer")                        #break                        self.onError()                        self.goReco()                        self.soundPeak = False                        while not self.soundPeak:                            pass                        self.start_zora()        self.logger.info("finished GA")        self.onStopped()        pass    def onInput_onStop(self):        self.onUnload() #it is recommended to reuse the clean-up as the box is stopped        self.onStopped() #activate the output of the box

I fixed all the parameters well but it doesn't want to work.