将音频文件分成几部分，但我需要在语音识别中使用这些文件

Question

我在 google 语音识别中遇到关于长音频文件的问题..所以我决定在 15 秒内拆分我的音频文件..每次我发送第一个 15 秒到语音识别然后第二个 15秒等等...

但现在当我使用 pydub lib 时它拆分音频文件，拆分后的 return 值不是文件扩展名，因为 API 需要文件扩展名作为参数（我标记了错误）它说“给定的音频文件必须是文件名字符串或类似文件的对象”

import speech_recognition as sr
import numpy

from os import path
AUDIO_FILE = "OAF_back_happy.wav"

from pydub import AudioSegment
sound = AudioSegment.from_wav("OAF_back_happy.wav")

halfway_point = len(sound) // 2
split = []
split.append(sound[:halfway_point])
split.append(sound[halfway_point:])
r = sr.Recognizer()

words=1
for x in split:
  with sr.AudioFile(x) as source:     #<-----
      audio = r.record(source)  # read the entire audio file
  try:
      # for testing purposes, we're just using the default API key
      # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
      # instead of `r.recognize_google(audio)`
      ans = r.recognize_google(audio)
      print("Google Speech Recognition thinks you said " +ans)
      for x in ans:
        if (x.isspace()) == True: 
          words+=1
      print(words) 
  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))

已编辑：如评论中所述，我不想导出文件，因为我正在使用服务器，我不想将同一个文件“放置两次”

Answer 1

未经测试，因为我懒得安装我不使用的软件包，但这就是我的意思。

for x in split:
    b = io.BytesIO()
    x.export(b)
    b.seek(0)
    with sr.AudioFile(b) as source:
        audio = r.record(source)

将音频文件分成几部分，但我需要在语音识别中使用这些文件

split audio file into parts but i need to use these files in speech recognition

python

speech-recognition

pydub

google-speech-api