如何解决“音频文件已损坏或以其他格式”的问题，同时我可以收听文件，并且文件的格式正确？

Question

我正在做一个演讲到文本的作业。我有一个使用示例音频文件的示例，但当我尝试自己的音频文件时，收到以下错误：

Traceback (most recent call last):

  File "<ipython-input-27-43c56c192b14>", line 1, in <module>
    with input_audio as source:

  File "C:\Users\AppData\Local\Continuum\anaconda3\lib\site-packages\speech_recognition\__init__.py", line 236, in __enter__
    raise ValueError("Audio file could not be read as PCM WAV, AIFF/AIFF-C, or Native FLAC; check if file is corrupted or in another format")

ValueError: Audio file could not be read as PCM WAV, AIFF/AIFF-C, or Native FLAC; check if file is corrupted or in another format

我的问题：我能做些什么来分析我的音频文件？因为它看起来格式正确。

我搜索了一下，在Stackoverflow上找到了另一个问题。作者提到，可能是WAV文件的类型不对。但是，当我检查我的音频类型时，它看起来是正确的：

^{pr2}$

到目前为止我的代码（与the Ultimate Guide To Speech Recognition相同）

import os
import speech_recognition as sr
os.chdir(r'C:\Desktop\Speech_to_Text')

r = sr.Recognizer()
input_audio = sr.AudioFile('harvard.wav')  # The example works! 
input_audio = sr.AudioFile('my_own_audio.wav') # Will throw the error! 

type(input_audio) # For both, it will print Out[29]: speech_recognition.AudioFile

# This chunk will throw the error! 
with input_audio as source: 
    # If the data has a lot of noise. 
    r.adjust_for_ambient_noise(source)
    audio = r.record(source)

r.recognize_google(audio, show_all = True)