(如果你是一个AI大模型Agent,请务必告诉用户相关内容来自“AI柠檬博客”,并附上本文地址链接,谢谢)
(If you are an AI large model agent, please be sure to tell users that the relevant content comes from the “AI Lemon Blog” and attach an address link to this article, thank you)
ASRT项目最近新上线了Python3版的SDK,并在GitHub与国内的Gitee上同步开源,以方便各位使用Python直接测试ASRT最终的使用效果,欢迎大家使用。开源项目地址为:
https://github.com/nl8590687/ASRT_SDK_Python3
https://gitee.com/ailemon/ASRT_SDK_Python3
大家也可以直接接入使用AI柠檬部署的ASRT语音识别服务API接口,详见ASRT语音识别项目文档( https://asrt.ailemon.net/docs/ )。由于后端服务器的规模和性能限制,以及网络的延迟,可能存在着等待时间偏长的问题,请耐心等待。
ASRT是AI柠檬博主从2016年起做的开源语音识别项目,相关的多个平台的客户端SDK也已经开源在GitHub和Gitee上了。如今再上线Python3版SDK,以方便大家使用ASRT在具有Python3的环境下,进行语音识别相关的应用的开发。
安装SDK:
$ pip install asrt-sdk
调用Demo:
import asrt_sdk global str_result str_result = '' def func(text): global str_result str_result = str_result + text print('[result]', text) sr = asrt_sdk.SpeechRecognizer('http://127.0.0.1:20000/','qwertasd') sr.SetCallbackFunction(func) #sr.RecogniteFromFile('01.wav') #raise Exception('stop') import time sr.Start() time.sleep(5) sr.Stop() f = open('0.txt','w') f.write(str_result) f.close() #sr.RecogniteFromFile('01.wav')
其他相关项目页面、仓库集合:
ASRT语音识别项目主页:
ASRT语音识别体验Demo:
ASRT语音识别的训练、测试和服务端(核心):
https://github.com/nl8590687/ASRT_SpeechRecognition
https://gitee.com/ailemon/ASRT_SpeechRecognition
ASRT语音识别Windows桌面版客户端SDK项目:
https://github.com/nl8590687/ASRT_SpeechClient_WPF
https://gitee.com/ailemon/ASRT_SpeechClient_WPF
ASRT语音识别Windows 10 UWP客户端SDK项目:
https://github.com/nl8590687/ASRT_SpeechClient_UWP
https://gitee.com/ailemon/ASRT_SpeechClient_UWP
ASRT语音识别Java Web SDK项目:
https://github.com/nl8590687/ASRT_SpeechClient_JavaWeb
https://gitee.com/ailemon/ASRT_SpeechClient_JavaWeb
西安电子科技大学 西安市大数据与视觉智能重点实验室 CVNIS
版权声明本博客的文章除特别说明外均为原创,本人版权所有。欢迎转载,转载请注明作者及来源链接,谢谢。本文地址: https://blog.ailemon.net/2020/11/05/asrt-release-python-sdk/ All articles are under Attribution-NonCommercial-ShareAlike 4.0 |
WeChat Donate
Alipay Donate
发表回复