如果您尝试做的只是语音到文本，那么这个简单的代码应该可以工作，首先运行pip install SpeechRecognition，然后这个代码应该可以工作

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    print("Listening...")
    audio = r.listen(source)

try:
    print("Recognizing...")
    text = r.recognize_google(audio)
    print("You said:", text)
except sr.UnknownValueError:
    print("Sorry, I could not understand your speech.")
except sr.RequestError as e:
    print("Sorry, an error occurred. {0}".format(e))