樹莓派語音聊天機器人

做一款樹莓派語音聊天機器人，網上有很多教程，其中有一個視頻教程，把相應資料做下整理：

樹莓派製作語音聊天機器人（傻瓜式教程）

以下爲視頻中代碼：

代碼一：測試程序

arecord -D "plughw:1" -f S16_LE -r 16000 -d 3 /home/pi/Desktop/voice.wav

代碼二

新建文件語音識別文件

sudo nano yuyinshibie.py

# coding: utf-8
import sys
import json
import urllib2
import base64
import requests
reload(sys)
sys.setdefaultencoding("utf-8")

def get_access_token():
        url = "https://openapi.baidu.com/oauth/2.0/token"
        body = {
                "grant_type":"client_credentials",
                "client_id" :"此處填寫自己的client_id",
                "client_secret":"此處填寫自己的client_secret",
        }
        r = requests.post(url,data=body,verify=True)
        respond = json.loads(r.text)
        return respond["access_token"]

def yuyinshibie_api(audio_data,token):
        speech_data = base64.b64encode(audio_data).decode("utf-8")
        speech_length = len(audio_data)
        post_data = {
                "format" : "wav",
                "rate" : 16000,
                "channel" : 1,
                "cuid" : "B8-27-EB-BA-24-14",
                "token" : token,
                "speech" : speech_data,
                "len" : speech_length
        }
        url = "http://vop.baidu.com/server_api"
        json_data = json.dumps(post_data).encode("utf-8")
        json_length = len(json_data)
        #print(json_data)

        req = urllib2.Request(url, data=json_data)
        req.add_header("Content-Type", "application/json")
        req.add_header("Content-Length", json_length)

        #print("asr start request\n")
        resp = urllib2.urlopen(req)
        #print("asr finish request\n")
        resp = resp.read()
        resp_data = json.loads(resp.decode("utf-8"))
        if resp_data["err_no"] == 0:
                return resp_data["result"]
        else:
                print(resp_data)
                return None

def asr_main(filename,tok):
        try:
                f = open(filename, "rb")
                audio_data = f.read()
                f.close()
                resp = yuyinshibie_api(audio_data,tok)
                return resp[0]
        except Exception,e:
                print "e:",e
                return "識別失敗".encode("utf-8")

代碼三

新建圖靈機器人文件

sudo nano Turling.py

# coding: utf-8

import requests
import json
import sys
reload(sys)
sys.setdefaultencoding("utf-8")


def Tuling(words):
    Tuling_API_KEY = "此處填寫自己的Turling KEY"

    body = {"key":Tuling_API_KEY,"info":words.encode("utf-8")}

    url = "http://www.tuling123.com/openapi/api"
    r = requests.post(url,data=body,verify=True)

    if r:
        date = json.loads(r.text)
        print date["text"]
        return date["text"]
    else:
        return None

代碼四

新建語音合成文件,代碼中涉及到的參數（如選擇機器人角色）可以查詢：百度官方文檔

sudo nano yuyinhecheng.py

# coding: utf-8
import sys
import urllib2
import json
import os
import yuyinshibie
reload(sys)
sys.setdefaultencoding("utf-8")

def yuyinhecheng_api(tok,tex):
        cuid = "B8-27-EB-BA-24-14"
        spd = "4"
        url = "http://tsn.baidu.com/text2audio?tex="+tex+"&lan=zh&cuid="+cuid+"$
        #print url
        #response = requests.get(url)
        #date = response.read()
        return url

def tts_main(filename,words,tok):
        voice_date = yuyinhecheng_api(tok,words)
        f = open(filename,"wb")
        f.write(voice_date)
        f.close()

代碼五

最後是語音機器人的主程序

sudo nano yuyin.py

# coding: utf-8

import os
import time
import yuyinhecheng
import Turling
import yuyinshibie


tok = yuyinshibie.get_access_token()

switch = True
while switch:
    os.system('sudo arecord -D "plughw:1" -f S16_LE -r 16000 -d 3 /home/pi/Desk$
    time.sleep(0.5)
    info = yuyinshibie.asr_main("/home/pi/Desktop/voice.wav",tok)
    if '關閉'.encode("utf-8") in info:
        while True:
            os.system('sudo arecord -D "plughw:1" -f S16_LE -r 16000 -d 10 /hom$
            time.sleep(10)

            info = yuyinshibie.asr_main("/home/pi/Desktop/voice.wav",tok)
            if '開啓'.encode("utf-8") in info:
                break

        url = "http://tsn.baidu.com/text2audio?tex=開啓成功&lan=zh&cuid=B8-27-E$
        os.system('mpg123 "%s"'%url)


    elif '暫停'.encode("utf-8") in info:
        url = "http://tsn.baidu.com/text2audio?tex=開始暫停&lan=zh&cuid=B8-27-E$
        os.system('mpg123 "%s"'%url)
        time.sleep(10)

        url = "http://tsn.baidu.com/text2audio?tex=暫停結束&lan=zh&cuid=B8-27-E$
        os.system('mpg123 "%s"'%url)
        continue
    else:
        tex = Turling.Tuling(info)
        url = yuyinhecheng.yuyinhecheng_api(tok,tex)
        os.system('mpg123 "%s"'%url)
        time.sleep(0.5)

運行

最後運行語音程序即可

sudo python yuyin.py

擴展

現在機器人只能進行語音對話，後續根據機器人的語音識別文字，獲取相應命令，與硬件機器人通信，就可以讓機器人動起來，比如語音控制開關等、語音小車聊天機器人等等