Python结合百度语音识别实现实时翻译软件的实现

Z时代
2024-01-10
分类：综合

一、所需库安装

pip install PyAudio

pip install SpeechRecognition

pip install baidu-aip

pip install Wave

pip install Wheel

pip install Pyinstaller

二、百度官网申请服务

三、源代码分享


import pyaudio
import wave
from aip import AipSpeech
import time
# 用Pyaudio库录制音频
#  out_file:输出音频文件名
#  rec_time:音频录制时间(秒)
def audio_record(out_file, rec_time):
  CHUNK = 1024
  FORMAT = pyaudio.paInt16 # 16bit编码格式
  CHANNELS = 1 # 单声道
  RATE = 16000 # 16000采样频率
  p = pyaudio.PyAudio()
  # 创建音频流
  stream = p.open(format=FORMAT, # 音频流wav格式
          channels=CHANNELS, # 单声道
          rate=RATE, # 采样率16000
          input=True,
          frames_per_buffer=CHUNK)
  print("开始记录语音{0}秒后开始识别...".format(rec_time))
  frames = [] # 录制的音频流
  # 录制音频数据
  for i in range(0, int(RATE / CHUNK * rec_time)):
    data = stream.read(CHUNK)
    frames.append(data)
  # 录制完成
  stream.stop_stream()
  stream.close()
  p.terminate()
  print("结束识别")
  # 保存音频文件
  wf = wave.open(out_file, 'wb')
  wf.setnchannels(CHANNELS)
  wf.setsampwidth(p.get_sample_size(FORMAT))
  wf.setframerate(RATE)
  wf.writeframes(b''.join(frames))
  wf.close()
def audio_recog(recogFile):
  # 读取文件
  def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
      return fp.read()
  # 识别本地文件
  result = client.asr(get_file_content(recogFile), 'wav', 16000, {'dev_pid': 1537,})
  return result
def write_file(file,text):
  import time
  time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
  f = open(file, 'a')
  f.write(time+':'+text+'\n')
  f.close()
audioFile="audio.wav"
textFile="识别结果.txt"
""" 你的 APPID AK SK """
APP_ID = '你的APP_ID'
API_KEY = '你的API_KEY'
SECRET_KEY = '你的SECRET_KEY'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
if __name__ == '__main__':
  while True:
    audio_record(audioFile, 5)
    textResult = audio_recog("audio.wav")
    if textResult['err_msg'] =="success.":
      print(textResult['result'])
      write_file(textFile,str(textResult['result']))