从音频文件读取数据时出现语音识别错误答案

【问题标题】：Speech recognition error while reading data from an audio file从音频文件读取数据时出现语音识别错误
【发布时间】：2024-01-01 05:13:01
【问题描述】：

这是我的代码：

import speech_recognition as sr

r = sr.Recognizer()
file = sr.AudioFile('E:/music/jack.wav')
with file as source:
    audio_file = r.record(source,duration=20)

print(r.recognize_google(source))

我收到此错误：

[Running] python -u "e:\Visual studio code\file-1.py"
Traceback (most recent call last):

  File "e:\Visual studio code\file-1.py", line 8, in <module>

    print(r.recognize_google(source))

  File "C:\Users\asus\AppData\Roaming\Python\Python39\site-packages\speech_recognition\__init__.py", line 822, in recognize_google

    assert isinstance(audio_data, AudioData), "``audio_data`` must be audio data"

AssertionError: ``audio_data`` must be audio data

我该如何解决这个问题？

【问题讨论】：

标签： python speech-recognition

【解决方案1】：

不要将source 提供给r.rcognize_google 的输入，而应提供audio_file 进行处理尝试一次！

import speech_recognition as sr

r = sr.Recognizer()
file = sr.AudioFile('E:/music/jack.wav')
with file as source:
    audio_file = r.record(source,duration=20)

print(r.recognize_google(audio_file))

【讨论】：