问Google语音识别库在Python有非常慢的speech_to_text()时代

EN

Me  -->  Sapphire what time is it
speech_to_text() Time =  5.611827599990647
Sapphire -->  16:46.
Listening...
Me  -->  ERROR
speech_to_text() Time =  3.4650153999973554
Listening...
Me  -->  ERROR
speech_to_text() Time =  6.241592899998068
Listening...
Me  -->  ERROR
speech_to_text() Time =  12.198483600004693
Listening...
Me  -->  ERROR
speech_to_text() Time =  3.7981161000061547
Listening...
Me  -->  shoe stamps
speech_to_text() Time =  51.52946890000021
Listening...
Me  -->  ERROR
speech_to_text() Time =  6.57019980000041
Listening...
Me  -->  ERROR
speech_to_text() Time =  46.647391800011974
Listening...

class ChatBot():
    def __init__(self, name):
        print("----- Starting up", name, "-----")
        self.name = name

    def speech_to_text(self):
        recognizer = sr.Recognizer()
        # with sr.Microphone(device_index=3) as mic:
        with sr.Microphone() as mic:
            recognizer.adjust_for_ambient_noise(mic)
            print("Listening...")
            audio = recognizer.listen(mic)
            self.text="ERROR"
        try:
            self.text = recognizer.recognize_google(audio)
            print("Me  --> ", self.text)
        except:
            print("Me  -->  ERROR")

    @staticmethod
    def text_to_speech(text):
        if text == "":
            print("ERROR")
        else:
            print((ai.name+" --> "), text)
            speaker = gTTS(text=text, lang="en", slow=False)
            speaker.save("res.mp3")

            vlc_instance = vlc.Instance("--no-video")
            player = vlc_instance.media_player_new()

            media = vlc_instance.media_new("res.mp3")

            player.set_media(media)
            player.play()


    def wake_up(self, text):
        return True if (self.name).lower() in text.lower() else False


def parse_input(txt):
    ## action time
    if "time" in txt and "is" in txt and "it" in txt:
        res = action_time()
    elif ai.name.lower() in txt:
        res = np.random.choice(
            ["That's me!, Sapphire!", "Hello I am Sapphire the AI", "Yes I am Sapphire!", "My name is Sapphire, okay?!", "I am Sapphire and I am alive!",
             "It's-a Me!, Sapphire!"])
    ## respond politely
    elif any(i in txt for i in ["thank", "thanks"]):
        res = np.random.choice(
            ["you're welcome!", "anytime!", "no problem!", "cool!", "I'm here if you need me!",
             "mention not."])
    elif any(i in txt for i in ["exit", "close"]):
        res = np.random.choice(
            ["Tata!", "Have a good day!", "Bye!", "Goodbye!", "Hope to meet soon!", "peace out!"])
        ex = False
    ## conversation
    else:
        if txt == "ERROR":
            # res="Sorry, come again?"
            res = ""
        else:
            starttime1 = timeit.default_timer()
            chat = nlp(transformers.Conversation(txt), pad_token_id=50256)
            endtime1 = timeit.default_timer()
            print("Transformer Time = ", (endtime1 - starttime1))
            res = str(chat)
            res = res[res.find("bot >> ") + 6:].strip()
    return res

def sapphire_audio():
    ex = True
    start = 0
    while ex:
        starttime1 = timeit.default_timer()
        ai.speech_to_text()
        endtime1 = timeit.default_timer()
        print("speech_to_text() Time = ", (endtime1 - starttime1))
        ## wake up
        if ai.wake_up(ai.text) is True:
            #remove Sapphire from phrase
            ai.text = ai.text.lower().replace(ai.name.lower(), "", 1)
            if start == 0:
                res = "Hello I am Sapphire the AI, what can I do for you?"
                start = 1
            else:
                res = parse_input(ai.text)
            ai.text_to_speech(res)

if __name__ == "__main__":

    os.environ["TOKENIZERS_PARALLELISM"] = "true"

    # sapphire_email()
    threading.Thread(target=sapphire_email).start()
    threading.Thread(target=sapphire_audio).start()