语音输入的猜数字小游戏

最近对语音输入比较感兴趣，然后将一个猜数字小游戏更改成了语音输入形式，下面是代码，有兴趣的朋友自己运行一下试试哦，很好玩。

import random
import win32com.client as win
import pyaudio # 这个需要自己下载*
import wave
from iat_ws_py3 import output
speak = win.Dispatch("SAPI.SpVoice")

speak.Speak('这是一个猜数字的小游戏，您需要猜1-100间的一个整数！')
num = random.randint(1, 100)
guess_chances = 7
speak.Speak('您只有7次猜数字的机会哦！')

def get_audio(in_path):
    # aa = str(input("是否开始录音？   （y/n）"))
    # if aa == str("y") :
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1  # 声道数
    RATE = 16000  # 采样率
    RECORD_SECONDS = 2  # 录音时间
    WAVE_OUTPUT_FILENAME = in_path
    p = pyaudio.PyAudio()

    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)

    print("*" * 5, "开始录音：请在5秒内输入语音", "*" * 5)
    frames = []
    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)
    print("*" * 5, "录音结束\n")

    stream.stop_stream()
    stream.close()
    p.terminate()

    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()
    # elif aa == str("n"):
    #     exit()
    # else:
    #     print("语音录入失败，请重新开始")
    #     get_audio(in_path)

for i in range(1, guess_chances + 1):
    aa = str(input("是否准备好了？   （y/n）"))
    if aa == str("y"):
        speak.Speak('这是第' + str(i) + '次猜数字')
        say = get_audio("./input.wav")
        guess=output()
        print('您猜的数是：',guess)
        if guess.isdigit():
            guess = int(guess)
            if guess < num:
                speak.Speak('您猜的数字太小了，您还有' + str(guess_chances - i) + '次机会，请重新输入：')
                print()
            elif guess > num:
                speak.Speak('您猜的数字太大了，您还有' + str(guess_chances - i) + '次机会，请重新输入：')
            elif guess == num:
                speak.Speak('恭喜您猜对了')
                break
        elif guess == '退出':
            speak.Speak('退出游戏！')
            break
        else:
            speak.Speak('输入的内容必须为整数，请重新输入：')
    elif aa == str("n"):
        exit()
    else:
        print("没有正确输入，请重新开始")

while (guess_chances - i) == 0:
    speak.Speak('您猜的次数已经超过7次，游戏结束！')
    break

下面是语音识别的代码，iat_ws.py3.py

import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
#from get_audio import get_audio # 导入录音.py文件

STATUS_FIRST_FRAME = 0  # 第一帧的标识
STATUS_CONTINUE_FRAME = 1  # 中间帧标识
STATUS_LAST_FRAME = 2  # 最后一帧的标识
vtext=0

class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret):
        self.APPID = ""
        self.APIKey = ''
        self.APISecret = ''


        # 公共参数(common)
        self.CommonArgs = {"app_id": self.APPID}
        # 业务参数(business)，更多个性化参数可在官网查看
        self.BusinessArgs = {"domain": "iat", "language": "zh_cn", "accent": "mandarin", "vinfo":1,"vad_eos":10000}

        # 采集音频 录音
        # get_audio("./input.wav")
        self.AudioFile = r"./input.wav"
    # 生成url
    def create_url(self):
        url = 'wss://ws-api.xfyun.cn/v2/iat'
        # 生成RFC1123格式的时间戳
        now = datetime.now()
        date = format_date_time(mktime(now.timetuple()))

        # 拼接字符串
        signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + "/v2/iat " + "HTTP/1.1"
        # 进行hmac-sha256进行加密
        signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),
                                 digestmod=hashlib.sha256).digest()
        signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (
            self.APIKey, "hmac-sha256", "host date request-line", signature_sha)
        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
        # 将请求的鉴权参数组合为字典
        v = {
            "authorization": authorization,
            "date": date,
            "host": "ws-api.xfyun.cn"
        }
        # 拼接鉴权参数，生成url
        url = url + '?' + urlencode(v)
        # print("date: ",date)
        # print("v: ",v)
        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致
        # print('websocket url :', url)
        return url

wsParam = Ws_Param(APPID=' ', APISecret=' ',
                   APIKey=' ')
websocket.enableTrace(False)
wsUrl = wsParam.create_url()

# 收到websocket消息的处理
def on_message(ws, message):
    global vtext
    try:
        code = json.loads(message)["code"]
        sid = json.loads(message)["sid"]
        if code != 0:
            errMsg = json.loads(message)["message"]
            print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))

        else:
            data = json.loads(message)["data"]["result"]["ws"]
            # print(json.loads(message))
            result = ""
            for i in data:
                for w in i["cw"]:
                    result += w["w"]
            #print("sid:%s call success!,data is:%s" % (sid, json.dumps(data, ensure_ascii=False)))
    except Exception as e:
        print("receive msg,but parse exception:", e)
    if len(data[0]['cw'][0]['w'])>0 :
        vtext=data[0]['cw'][0]['w']
        print('vtext=',vtext)
# 收到websocket错误的处理
def on_error(ws, error):
    print("### error:", error)


# 收到websocket关闭的处理
def on_close(ws):
    print("### closed ###")


# 收到websocket连接建立的处理
def on_open(ws):
    def run(*args):
        frameSize = 8000  # 每一帧的音频大小
        intervel = 0.04  # 发送音频间隔(单位:s)
        status = STATUS_FIRST_FRAME  # 音频的状态信息，标识音频是第一帧，还是中间帧、最后一帧

        with open(wsParam.AudioFile, "rb") as fp:
            while True:
                buf = fp.read(frameSize)
                # 文件结束
                if not buf:
                    status = STATUS_LAST_FRAME
                # 第一帧处理
                # 发送第一帧音频，带business 参数
                # appid 必须带上，只需第一帧发送
                if status == STATUS_FIRST_FRAME:

                    d = {"common": wsParam.CommonArgs,
                         "business": wsParam.BusinessArgs,
                         "data": {"status": 0, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    d = json.dumps(d)
                    ws.send(d)
                    status = STATUS_CONTINUE_FRAME
                # 中间帧处理
                elif status == STATUS_CONTINUE_FRAME:
                    d = {"data": {"status": 1, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    ws.send(json.dumps(d))
                # 最后一帧处理
                elif status == STATUS_LAST_FRAME:
                    d = {"data": {"status": 2, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    ws.send(json.dumps(d))
                    time.sleep(1)
                    break
                # 模拟音频采样间隔
                time.sleep(intervel)
        ws.close()

    thread.start_new_thread(run, ())

def output():
    ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)
    ws.on_open = on_open
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
    print(vtext)
    return vtext


**语音识别用的是讯飞语音公司的开放链接，大家可以到网址https://www.xfyun.cn/自己注册个账号，然后申请个接口就可以进行语音识别啦！**

本文地址：https://blog.csdn.net/weixin_41602460/article/details/112601436