# -*- coding:utf-8 -*- # # Author: njnuko # Email: njnuko@163.com # # 这个文档是基于官方的demo来改的，固体官方demo文档请参考官网 # # 语音听写流式 WebAPI 接口调用示例 接口文档（必看）：https://doc.xfyun.cn/rest_api/语音听写（流式版）.html # webapi 听写服务参考帖子（必看）：http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=38947&extra= # 语音听写流式WebAPI 服务，热词使用方式：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--个性化热词， # 设置热词 # 注意：热词只能在识别的时候会增加热词的识别权重，需要注意的是增加相应词条的识别率，但并不是绝对的，具体效果以您测试为准。 # 语音听写流式WebAPI 服务，方言试用方法：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--识别语种列表 # 可添加语种或方言，添加后会显示该方言的参数值 # 错误码链接：https://www.xfyun.cn/document/error-code （code返回错误码时必看） # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 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 import os import wave 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 ############# #whole_dict 是用来存储返回值的，由于带语音修正，所以用dict来存储，有更新的化pop之前的值，最后再合并 global whole_dict #这个文档是官方文档改的，这个参数是用来做函数调用时用的 global wsParam ############## class Ws_Param(object): # 初始化 def __init__(self, APPID, APIKey, APISecret,BusinessArgs, AudioFile): self.APPID = APPID self.APIKey = APIKey self.APISecret = APISecret self.AudioFile = AudioFile self.BusinessArgs = BusinessArgs # 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} # 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 # 收到websocket消息的处理 def on_message(ws, message): global whole_dict 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: temp1 = json.loads(message)["data"]["result"] data = json.loads(message)["data"]["result"]["ws"] sn = temp1["sn"] if "rg" in temp1.keys(): rep = temp1["rg"] rep_start = rep[0] rep_end = rep[1] for sn in range(rep_start,rep_end+1): #print("before pop",whole_dict) #print("sn",sn) whole_dict.pop(sn,None) #print("after pop",whole_dict) results = "" for i in data: for w in i["cw"]: results += w["w"] whole_dict[sn]=results #print("after add",whole_dict) else: results = "" for i in data: for w in i["cw"]: results += w["w"] whole_dict[sn]=results #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) # 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,a,b): print("### closed ###") # 收到websocket连接建立的处理 def on_open(ws): global wsParam 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 wave.open(wsParam.AudioFile, "rb") as fp: while True: buf = fp.readframes(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, ()) #提供给xunfei_voice调用的函数 def xunfei_asr(APPID,APISecret,APIKey,BusinessArgsASR,AudioFile): global whole_dict global wsParam whole_dict = {} wsParam1 = Ws_Param(APPID=APPID, APISecret=APISecret, APIKey=APIKey,BusinessArgs=BusinessArgsASR, AudioFile=AudioFile) #wsParam是global变量，给上面on_open函数调用使用的 wsParam = wsParam1 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_open ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE}) #把字典的值合并起来做最后识别的输出 whole_words = "" for i in sorted(whole_dict.keys()): whole_words += whole_dict[i] return whole_words