python調(diào)用百度語音REST API

#!/usr/bin/python3

import urllib.request
import urllib
import json
import base64
class BaiduRest:
  def __init__(self, cu_id, api_key, api_secert):
    # token認(rèn)證的url
    self.token_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s"
    # 語音合成的resturl
    self.getvoice_url = "http://tsn.baidu.com/text2audio?tex=%s&lan=zh&cuid=%s&ctp=1&tok=%s"
    # 語音識(shí)別的resturl
    self.upvoice_url = 'http://vop.baidu.com/server_api'

    self.cu_id = cu_id
    self.getToken(api_key, api_secert)
    return

  def getToken(self, api_key, api_secert):
    # 1.獲取token
    token_url = self.token_url % (api_key,api_secert)

    r_str = urllib.request.urlopen(token_url).read()
    token_data = json.loads(r_str)
    self.token_str = token_data['access_token']
    pass

  def getVoice(self, text, filename):
    # 2. 向Rest接口提交數(shù)據(jù)
    get_url = self.getvoice_url % (urllib.parse.quote(text), self.cu_id, self.token_str)

    voice_data = urllib.request.urlopen(get_url).read()
    # 3.處理返回?cái)?shù)據(jù)
    voice_fp = open(filename,'wb+')
    voice_fp.write(voice_data)
    voice_fp.close()
    pass

  def getText(self, filename):
    # 2. 向Rest接口提交數(shù)據(jù)
    data = {}
    # 語音的一些參數(shù)
    data['format'] = 'wav'
    data['rate'] = 8000
    data['channel'] = 1
    data['cuid'] = self.cu_id
    data['token'] = self.token_str
    wav_fp = open(filename,'rb')
    voice_data = wav_fp.read()
    data['len'] = len(voice_data)
    data['speech'] = base64.b64encode(voice_data).decode('utf-8')
    post_data = json.dumps(data)
    r_data = urllib.request.urlopen(self.upvoice_url,data=bytes(post_data,encoding="utf-8")).read()
    # 3.處理返回?cái)?shù)據(jù)
    return json.loads(r_data)['result']

if __name__ == "__main__":
  # 我的api_key,供大家測(cè)試用，在實(shí)際工程中請(qǐng)換成自己申請(qǐng)的應(yīng)用的key和secert
  api_key = "SrhYKqzl3SE1URnAEuZ0FKdT" 
  api_secert = "hGqeCkaMPb0ELMqtRGc2VjWdmjo7T89d"
  # 初始化
  bdr = BaiduRest("test_python", api_key, api_secert)
  # 將字符串語音合成并保存為out.mp3
  bdr.getVoice("你好北京郵電大學(xué)!", "out.mp3")
  # 識(shí)別test.wav語音內(nèi)容并顯示
  print(bdr.getText("out.wav"))

#!/usr/bin/python3
# -*- coding: utf-8 -*-

from pyaudio import PyAudio, paInt16 
import numpy as np 
from datetime import datetime 
import wave

class recoder:
  NUM_SAMPLES = 2000   #pyaudio內(nèi)置緩沖大小
  SAMPLING_RATE = 8000  #取樣頻率
  LEVEL = 500     #聲音保存的閾值
  COUNT_NUM = 20   #NUM_SAMPLES個(gè)取樣之內(nèi)出現(xiàn)COUNT_NUM個(gè)大于LEVEL的取樣則記錄聲音
  SAVE_LENGTH = 8     #聲音記錄的最小長(zhǎng)度：SAVE_LENGTH * NUM_SAMPLES 個(gè)取樣
  TIME_COUNT = 60   #錄音時(shí)間，單位s

  Voice_String = []

  def savewav(self,filename):
    wf = wave.open(filename, 'wb') 
    wf.setnchannels(1) 
    wf.setsampwidth(2) 
    wf.setframerate(self.SAMPLING_RATE) 
    wf.writeframes(np.array(self.Voice_String).tostring()) 
    # wf.writeframes(self.Voice_String.decode())
    wf.close() 

  def recoder(self):
    pa = PyAudio() 
    stream = pa.open(format=paInt16, channels=1, rate=self.SAMPLING_RATE, input=True, 
      frames_per_buffer=self.NUM_SAMPLES) 
    save_count = 0 
    save_buffer = [] 
    time_count = self.TIME_COUNT

    while True:
      time_count -= 1
      # print time_count
      # 讀入NUM_SAMPLES個(gè)取樣
      string_audio_data = stream.read(self.NUM_SAMPLES) 
      # 將讀入的數(shù)據(jù)轉(zhuǎn)換為數(shù)組
      audio_data = np.fromstring(string_audio_data, dtype=np.short)
      # 計(jì)算大于LEVEL的取樣的個(gè)數(shù)
      large_sample_count = np.sum( audio_data > self.LEVEL )
      print(np.max(audio_data))
      # 如果個(gè)數(shù)大于COUNT_NUM，則至少保存SAVE_LENGTH個(gè)塊
      if large_sample_count > self.COUNT_NUM:
        save_count = self.SAVE_LENGTH 
      else: 
        save_count -= 1

      if save_count < 0:
        save_count = 0 

      if save_count > 0 : 
      # 將要保存的數(shù)據(jù)存放到save_buffer中
        #print save_count > 0 and time_count >0
        save_buffer.append( string_audio_data ) 
      else: 
      #print save_buffer
      # 將save_buffer中的數(shù)據(jù)寫入WAV文件，WAV文件的文件名是保存的時(shí)刻
        #print "debug"
        if len(save_buffer) > 0 : 
          self.Voice_String = save_buffer
          save_buffer = [] 
          print("Recode a piece of voice successfully!")
          return True
      if time_count==0: 
        if len(save_buffer)>0:
          self.Voice_String = save_buffer
          save_buffer = [] 
          print("Recode a piece of voice successfully!")
          return True
        else:
          return False

if __name__ == "__main__":
  r = recoder()
  r.recoder()
  r.savewav("test.wav")