張
更新時間：2022/4/12 上午 11:41:24

機器學習與深度學習特訓班 第二版 第九章

在這個程式執行


import speech_recognition as sr

r = sr.Recognizer()  #建立語音辨識物件
with sr.WavFile("record1.wav") as source:  #讀取語音檔
    audio = r.record(source)

print('開始翻譯...')
try:
    text = r.recognize_google(audio, language="zh-TW")  #辨識結果
    print(text)
except sr.UnknownValueError:
    print("Google Speech Recognition 無法辨識此語音！")
except sr.RequestError as e:
    print("無法由 Google Speech Recognition 取得結果; {0}".format(e))
print('翻譯結束！')

他跑出了這樣的錯誤
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-1-e39edd4fbc55> in <module>
      2
      3 r = sr.Recognizer()  #建立語音辨識物件
----> 4 with sr.WavFile("record1.wav") as source:  #讀取語音檔
      5     audio = r.record(source)
      6

C:\ProgramData\Anaconda3\lib\site-packages\speech_recognition\__init__.py in __enter__(self)
    201         try:
    202             # attempt to read the file as WAV
--> 203             self.audio_reader = wave.open(self.filename_or_fileobject, "rb")
    204             self.little_endian = True  # RIFF WAV is a little-endian format (most ``audioop`` operations assume that the frames are stored in little-endian form)
    205         except (wave.Error, EOFError):

C:\ProgramData\Anaconda3\lib\wave.py in open(f, mode)
    508             mode = 'rb'
    509     if mode in ('r', 'rb'):
--> 510         return Wave_read(f)
    511     elif mode in ('w', 'wb'):
    512         return Wave_write(f)

C:\ProgramData\Anaconda3\lib\wave.py in __init__(self, f)
    158         self._i_opened_the_file = None
    159         if isinstance(f, str):
--> 160             f = builtins.open(f, 'rb')
    161             self._i_opened_the_file = f
    162         # else, assume it is an open file object already

FileNotFoundError: [Errno 2] No such file or directory: 'record1.wav'

他說找不到檔案 但我不管在本書範例的路徑以及下載的地方都有放了record1.wav的語音檔了 但他還是說找不到

文淵閣工作室
更新時間：2022/4/12 下午 08:07:03

剛才測試此範例執行正常。
record1.wav 需和 voiceReg1.py 在同一資料夾。(直接在書附範例資料夾執行即可)