語音識別的 Python 代碼不起作用

Question

我瀏覽了有關此主題的所有類似問題並嘗試了所有方法，但沒有任何效果。

我嘗試了以下鏈接中的解決方案： 語音識別 python 停止監聽SpeechRecognition 產生 OSError: No Default Input Device Available Python，Speech Recognition 卡在“Listening...” 語音識別 python 代碼不起作用等。

import speech_recognition as sr

def get_audio():
    r =  sr.Recognizer()

    with sr.Microphone() as source:
        r.adjust_for_ambient_noise(source, duration=5)
        print("listening... ")
        audio = r.listen(source)
        said = ""

        try:
            said = r.recognize_google(audio)
        except sr.UnknownValueError:
            print("Google Speech Recognition could not understand audio")
        except sr.RequestError as e:
            print("Could not request results from Google Speech Recognition service; {0}".format(e))

    return said.lower()         

print(get_audio())

我得到的錯誤是：

json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

以下命令卡在“說點什么……”並且什么也不做。

 python -m speech_recognition 

我還嘗試了以下代碼來檢查默認音頻設備：

import pyaudio
print(pyaudio.pa.get_default_input_device())

輸出：

OSError: No Default Input Device Available

我在這里做錯了什么？

Answer 1

正如上面的評論中所說，您似乎沒有任何可用的麥克風。

在使用語音識別時，我通常會在聽之前詢問用戶使用哪種設備。

例如，使用這個實現：

# Identify the microphone device to use
def get_microphone_device():
    microphone_list = []
    for index, name in enumerate(sr.Microphone.list_microphone_names()):
        microphone_list.append("Microphone {1} `(device_index={0})`".format(index, name))

    questions = [
    inquirer.List('microphone',
            message = "What Microphone will you use?",
            choices = microphone_list,
        ),
    ]
    answers = inquirer.prompt(questions)
    microphone = answers["microphone"]
    microphone = re.search("(?=`)(.*)", microphone).group(0)
    device = re.search("[0-9]", microphone).group()
    return device

然后，要使用設備並獲取消息，您可以按照您的方式進行操作，例如：

# Listen to the speaker through the microphone device
def get_speech(device):
    rec = sr.Recognizer()
    with sr.Microphone(device_index=int(device)) as source:
        print("Speak, we are listening:")
        audio = rec.listen(source)
        try:
            text = rec.recognize_google(audio)
            print("You said: \"{}\"".format(text))
        except:
            print("Sorry, we couldn't recognize what you said")
    return text

這是完整實現的示例

我希望它有幫助！