Question

当我运行此代码并说出脚本时，返回空列表：

import pyaudio
import pyttsx3
import os
import pyautogui
import speech_recognition as sr
def command():
    r = sr.Recognizer()
    mic = sr.Microphone()
    recog = sr.Recognizer()
    with mic as u_audio:
        print('Speak please')
        r.adjust_for_ambient_noise(u_audio)
        voice = r.listen(u_audio)
    try:
        listening = recog.recognize_google(voice, language = 'en-EN', show_all = True)
        print(listening)
    except Exception as e:
        print('I not understand' + str(e))
        command()

command()

输出：请说 [] 我不明白，为什么列表是空的。也许我应该选择麦克风索引。

Answer 1

麦克风是问题

问题应该出在麦克风上，因为我运行了相同的代码，它确实给出了输出，给出了演讲的所有可能结果。

不管怎样，效率不高。不需要的库会减慢速度，这是更新的代码：

import pyttsx3
import speech_recognition as sr

def command():
    r = sr.Recognizer()
    mic = sr.Microphone()
    recog = sr.Recognizer()

    with mic as u_audio:
        r.adjust_for_ambient_noise(u_audio)
        print('Speak please')
        voice = r.listen(u_audio)
    try:
        listening = recog.recognize_google(voice, language = 'en-EN', show_all = True)
        print(listening)

    except Exception as e:
        print('I not understand' + str(e))
        command()

command()

评论结果！

Python语音识别

1 个答案: