失眠网 > 语音识别（利用python将语音转化为文字）

语音识别（利用python将语音转化为文字）

时间：2019-07-10 01:58:33

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

文章目录

前言一、申请讯飞语音端口1.点击链接进入讯飞平台主页面2.在页面注册自己的个人账户3.申请语音端口4.查看自己的端口编码二、python代码讲解1.代码如下（实例）2.代码需要修改的部分3.包的导入4.结果演示5.代码所借鉴的原链接总结

前言

本篇博客讲述利用讯飞端口将语音转化为文字。

一、申请讯飞语音端口

1.点击链接进入讯飞平台主页面

2.在页面注册自己的个人账户

ps：注册账户是完全免费的，因为我之前已经注册过一个了，这里就不重复介绍了，注册之后看个人情况进行个人认证，这个不影响之后的操作。

3.申请语音端口

ps:申请内容大概像我这样写就行，名字重复的话换一个

4.查看自己的端口编码

二、python代码讲解

1.代码如下（实例）

代码如下（示例）：

#使用语音import threadingimport websocketimport hashlibimport base64import hmacimport jsonfrom urllib.parse import urlencodeimport time# 该模块为客户端和服务器端的网络套接字提供对传输层安全性(通常称为“安全套接字层”)# 的加密和对等身份验证功能的访问。import sslfrom wsgiref.handlers import format_date_timefrom datetime import datetimefrom time import mktimeimport _thread as threadimport pyaudioSTATUS_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class Ws_Param(object):# 初始化def __init__(self, APPID, APIKey, APISecret):self.APPID = APPIDself.APIKey = APIKeyself.APISecret = APISecret# 公共参数(common)monArgs = {"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}# 生成urldef create_url(self):url = 'wss://ws-/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-" + "\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-"}# 拼接鉴权参数，生成urlurl = 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# 收到websocket消息的处理def on_message(ws, message):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"]result = ""for i in data:for w in i["cw"]:result += w["w"]if result == '。' or result == '.。' or result == ' .。' or result == ' 。':passelse:#t.insert(END, result) # 把上边的标点插入到result的最后print("翻译结果: %s。" % (result))except Exception as e:print("receive msg,but parse exception:", e)# 收到websocket错误的处理def on_error(ws, error):print("### error:", error)run()# 收到websocket关闭的处理def on_close(ws):pass# 收到websocket连接建立的处理def on_open(ws):def run(*args):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CHUNK = 520 # 定义数据流块FORMAT = pyaudio.paInt16 # 16bit编码格式CHANNELS = 1 # 单声道RATE = 16000 # 16000采样频率# 实例化pyaudio对象p = pyaudio.PyAudio() # 录音# 创建音频流# 使用这个对象去打开声卡，设置采样深度、通道数、采样率、输入和采样点缓存数量stream = p.open(format=FORMAT, # 音频流wav格式channels=CHANNELS, # 单声道rate=RATE, # 采样率16000input=True,frames_per_buffer=CHUNK)print("- - - - - - - Start Recording ...- - - - - - - ")# 添加开始表示 ——start recording——global texttip = "——start recording——"for i in range(0, int(RATE / CHUNK * 60)):# # 读出声卡缓冲区的音频数据buf = stream.read(CHUNK)if not buf:status = STATUS_LAST_FRAMEif status == STATUS_FIRST_FRAME:d = {"common": monArgs,"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)breakthread.start_new_thread(run, ())def run():global wsParam# 讯飞接口编码wsParam = Ws_Param(APPID='',APIKey='',APISecret='')websocket.enableTrace(False)wsUrl = wsParam.create_url()ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)ws.on_open = on_openws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE}, ping_timeout=2)def runc():run()class Job(threading.Thread):def __init__(self, *args, **kwargs):super(Job, self).__init__(*args, **kwargs)self.__flag = threading.Event() # 用于暂停线程的标识self.__flag.set() # 设置为Trueself.__running = threading.Event() # 用于停止线程的标识self.__running.set() # 将running设置为Truedef run(self):while self.__running.isSet():self.__flag.wait() # 为True时立即返回, 为False时阻塞直到内部的标识位为True后返回runc()time.sleep(1)def pause(self):self.__flag.clear() # 设置为False, 让线程阻塞def resume(self):self.__flag.set() # 设置为True, 让线程停止阻塞def stop(self):self.__flag.set() # 将线程从暂停状态恢复, 如何已经暂停的话self.__running.clear() # 设置为Falsea = Job()a.start()