概述
1.在控制台创建应用获取三元组信息
2.下载示例代码,本地运行一下,然后根据需要改写代码:
语音听写示例代码:
# -*- coding:utf-8 -*-
#
# author: iflytek
#
# 本demo测试时运行的环境为:Windows + Python3.7
# 本demo测试成功运行时所安装的第三方库及其版本如下,您可自行逐一或者复制到一个新的txt文件利用pip一次性安装:
# cffi==1.12.3
# gevent==1.4.0
# greenlet==0.4.15
# pycparser==2.19
# six==1.12.0
# websocket==0.2.1
# websocket-client==0.56.0
#
# 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
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
class Ws_Param(object):
# 初始化
def __init__(self, APPID, APIKey, APISecret, AudioFile):
self.APPID = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.AudioFile = AudioFile
# 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):
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)
# 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, ())
if __name__ == "__main__":
# 测试时候在此处正确填写相关信息即可运行
time1 = datetime.now()
wsParam = Ws_Param(APPID='535sdgcgsc4c', APIKey='481607dsghdsfhsd62e89a350a55b',
APISecret='0wert346tgertg44332cad57c53',
AudioFile=r'C:\Users\Desktop\深度学习\iat_pcm_8k.pcm')
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})
time2 = datetime.now()
print(time2-time1)
返回结果:
sid:iat0007be39@dx1738e7d0f377a1d802 call success!,data is:[{"cw": [{"sc": 0, "w": "我"}], "bg": 25}, {"bg": 41, "cw": [{"sc": 0, "w": "工作"}]}, {"bg": 121, "cw": [{"w": "做", "sc":
0}]}, {"bg": 177, "cw": [{"sc": 0, "w": "得"}]}, {"bg": 185, "cw": [{"sc": 0, "w": "很好"}]}]
sid:iat0007be39@dx1738e7d0f377a1d802 call success!,data is:[{"cw": [{"sc": 0, "w": "。"}], "bg": 0}]
### closed ###
0:00:03.570561
语音合成代码示例:
# -*- coding:utf-8 -*-
#
# author: iflytek
#
# 本demo测试时运行的环境为:Windows + Python3.7
# 本demo测试成功运行时所安装的第三方库及其版本如下:
# cffi==1.12.3
# gevent==1.4.0
# greenlet==0.4.15
# pycparser==2.19
# six==1.12.0
# websocket==0.2.1
# websocket-client==0.56.0
# 合成小语种需要传输小语种文本、使用小语种发音人vcn、tte=unicode以及修改文本编码方式
# 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
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
class Ws_Param(object):
# 初始化
def __init__(self, APPID, APIKey, APISecret, Text):
self.APPID = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.Text = Text
# 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 = {"aue": "raw", "auf": "audio/L16;rate=16000", "vcn": "xiaoyan", "tte": "utf8"}
self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}
#使用小语种须使用以下方式,此处的unicode指的是 utf16小端的编码方式,即"UTF-16LE"”
#self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-16')), "UTF8")}
# 生成url
def create_url(self):
url = 'wss://tts-api.xfyun.cn/v2/tts'
# 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/tts " + "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
def on_message(ws, message):
try:
message =json.loads(message)
code = message["code"]
sid = message["sid"]
audio = message["data"]["audio"]
audio = base64.b64decode(audio)
status = message["data"]["status"]
print(message)
if status == 2:
print("ws is closed")
ws.close()
if code != 0:
errMsg = message["message"]
print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))
else:
with open('./demo.pcm', 'ab') as f:
f.write(audio)
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):
print("### closed ###")
# 收到websocket连接建立的处理
def on_open(ws):
def run(*args):
d = {"common": wsParam.CommonArgs,
"business": wsParam.BusinessArgs,
"data": wsParam.Data,
}
d = json.dumps(d)
print("------>开始发送文本数据")
ws.send(d)
if os.path.exists('./demo.pcm'):
os.remove('./demo.pcm')
thread.start_new_thread(run, ())
if __name__ == "__main__":
# 测试时候在此处正确填写相关信息即可运行
wsParam = Ws_Param(APPID='535fa4c', APIKey='4816egesrt3453289a350a55b',
APISecret='0546drgdesgfdhtrhudsget32d7b232cad57c53',
Text="这是一个语音合成示例")
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})
返回结果:
包含编码数据和PCM音频文件
------>开始发送文本数据
{'code': 0, 'message': 'success', 'sid': 'tts0006001e@dx1738e7139b87a1c902', 'data': {'audio': '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}
最后
以上就是昏睡航空为你收集整理的科大讯飞语音识别语音合成webAPI调用示例(基于Python)的全部内容,希望文章能够帮你解决科大讯飞语音识别语音合成webAPI调用示例(基于Python)所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错,欢迎将靠谱客网站推荐给程序员好友。
本图文内容来源于网友提供,作为学习参考使用,或来自网络收集整理,版权属于原作者所有。
发表评论 取消回复