5

这是我的代码：

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    print('Say Something')
    audio = r.listen(source)
    voice_data = r.record(audio)
    print(voice_data)

当我在终端上键入“python main.py”并启动程序时，它开始收听但听不到我说的话。我尝试使用adjust_for_ambient_noise() 而不是，listen()但它也没有改变任何东西。

我正在使用 macOS Catalina 和 Python 3.8.1。

这是我得到的错误：

Traceback (most recent call last):
  File "main.py", line 8, in <module>
    voice_data = r.record(audio)
  File "/Users/sefailyasoz/PycharmProjects/SpeechAssistant/venv/lib/python3.8/site-packages/speech_recognition/__init__.py", line 483, in record
    assert isinstance(source, AudioSource), "Source must be an audio source"
AssertionError: Source must be an audio source

这是我使用时得到的adjust_for_ambient_noise()，如果我使用listen，它不会结束，它只是听，我用 结束它Ctrl+C。

4

2 回答 2

1

好吧，我稍微改变了我的功能

def record_audio(ask=False):
    with sr.Microphone() as source:
        if ask:
            turkishSiri_speak(ask)
        audio = r.listen(source)
        voice_data = ''
        try:
            voice_data = r.recognize_google(audio , language='tr-TR')
        except sr.UnknownValueError:
            turkishSiri_speak('Ne söylediğini anlayamadım')
        except sr.RequestError:
            turkishSiri_speak('Google konuşma servisinde bir problem var')
        return voice_data

但最大的问题是 macOS 问题，我必须允许 pycharm 或 Visual Studio 代码使用我的麦克风。在更改功能之前它已经在给予许可后工作

于 2020-05-14T16:18:26.053 回答
0

您在此处使用函数 record()，该函数用于从文件中捕获数据，您应该在捕获麦克风输入时使用 listen() 函数。 

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    print('Say Something')
    audio = r.listen(source)
    print(audio) #This is just a speech_recognition.AudioData object
    text = r.recognize_google(audio) #Speech to text google recognizer
    print(text) #This is what you actually said
于 2020-05-13T02:25:37.650 回答