-
问题:---------------------------------------------------------------------------在Hilens studio中测试pyttsx3文本转音频,出现错误注:已安装pyttsx包和espeak包源代码如下:-------------------------------------------------------------------------#! /usr/bin/python3.7import osimport cv2import hilensimport pyttsx3import espeakdef run(work_path): # 系统初始化,参数要与创建技能时填写的检验值保持一致 hilens.init("hello") engine = pyttsx3.init() engine.say('HERE PASS THE TEXT TO CONVERT INTO SPEECH') engine.runAndWait()if __name__ == "__main__": run(os.getcwd())错误提示:-------------------------------------------------------------------------[huser@studio-ide-679f67bb45-866xw Hello_haq]$ cd /home/huser/projects/Hello_haq[huser@studio-ide-679f67bb45-866xw Hello_haq]$ python3 /home/huser/projects/Hello_haq/start.pyTraceback (most recent call last): File "/home/huser/projects/Hello_haq/start.py", line 5, in <module> import main File "./src/main/python/main.py", line 7, in <module> import espeakModuleNotFoundError: No module named 'espeak'[huser@studio-ide-679f67bb45-866xw Hello_haq]$ pip3 install espeak --userWARNING: When the --extra-index-url option is used, the installation package is downloaded from an unverified URL. Exercise caution when using this option.Looking in indexes: http://mirrors.myhuaweicloud.com/pypi/web/simpleCollecting espeak Downloading http://mirrors.myhuaweicloud.com/pypi/web/packages/31/36/30bbc9d4d8a3d7e5edc046cfaf0410434f583a36461122849c1cdfd363eb/espeak-0.1.0.tar.gzRequirement already satisfied: requests in /usr/lib64/python3.7/site-packages (from espeak) (2.26.0)Requirement already satisfied: certifi>=2017.4.17 in /usr/lib64/python3.7/site-packages (from requests->espeak) (2021.10.8)Requirement already satisfied: charset-normalizer~=2.0.0; python_version >= "3" in /usr/lib64/python3.7/site-packages (from requests->espeak) (2.0.7)Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/lib64/python3.7/site-packages (from requests->espeak) (1.26.7)Requirement already satisfied: idna<4,>=2.5; python_version >= "3" in /usr/lib64/python3.7/site-packages (from requests->espeak) (3.3)Installing collected packages: espeak Running setup.py install for espeak ... doneSuccessfully installed espeak-0.1.0[huser@studio-ide-679f67bb45-866xw Hello_haq]$ cd /home/huser/projects/Hello_haq[huser@studio-ide-679f67bb45-866xw Hello_haq]$ python3 /home/huser/projects/Hello_haq/start.py[SFW]2022-06-18 09:00:14.889[INFO](14031-device_checker.cpp:71)----- start DetectDevice ------[DEVICE]2022-06-18 09:00:14.911[INFO](14031-acl_mediaplugin.cpp:19)-----------load acl_C75 Media---------[DEVICE]2022-06-18 09:00:15.163[INFO](14031-acl_inferplugin.cpp:26)-----------load acl_C75 Infer---------Traceback (most recent call last): File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/__init__.py", line 20, in init eng = _activeEngines[driverName] File "/usr/lib64/python3.7/weakref.py", line 137, in __getitem__ o = self.data[key]()KeyError: NoneDuring handling of the above exception, another exception occurred:Traceback (most recent call last): File "/home/huser/projects/Hello_haq/start.py", line 17, in <module> main.run(work_path) File "./src/main/python/main.py", line 13, in run engine = pyttsx3.init() File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/__init__.py", line 22, in init eng = Engine(driverName, debug) File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/engine.py", line 30, in __init__ self.proxy = driver.DriverProxy(weakref.proxy(self), driverName, debug) File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/driver.py", line 50, in __init__ self._module = importlib.import_module(name) File "/usr/lib64/python3.7/importlib/__init__.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 1006, in _gcd_import File "<frozen importlib._bootstrap>", line 983, in _find_and_load File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 677, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 728, in exec_module File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/drivers/espeak.py", line 9, in <module> from . import _espeak, toUtf8, fromUtf8 File "/home/huser/.local/lib/python3.7/site-packages/pyttsx3/drivers/_espeak.py", line 18, in <module> dll = cdll.LoadLibrary('libespeak.so.1') File "/usr/lib64/python3.7/ctypes/__init__.py", line 437, in LoadLibrary return self._dlltype(name) File "/usr/lib64/python3.7/ctypes/__init__.py", line 359, in __init__ self._handle = _dlopen(self._name, mode)OSError: libespeak.so.1: cannot open shared object file: No such file or directory麻烦帮忙看下如何解决,谢谢!截图如下:-----------------------------------------------------------------------
-
问题:---------------------------------------------------------------------------在Hilens studio中测试输出音频,显示错误将技能安装到Hilens中亦没有任何输出注1:Hilens固件版本:1.3.3;注2:附件中包括acc音频文件源代码如下:-------------------------------------------------------------------------#! /usr/bin/python3.7import osimport hilens# import wavedef run(work_path): # 系统初始化,参数要与创建技能时填写的检验值保持一致 hilens.init("hello") audio_out = hilens.AudioOutput() audio_out.play_aac_file(os.path.join(work_path, 'rain.acc'), 3) hilens.terminate()if __name__ == "__main__": run(os.getcwd())错误提示:-------------------------------------------------------------------------cd /home/huser/projects/Hello_World_Python_haqpython3 /home/huser/projects/Hello_World_Python_haq/start.py[huser@studio-ide-679f67bb45-866xw ~]$ cd /home/huser/projects/Hello_World_Python_haq[huser@studio-ide-679f67bb45-866xw Hello_World_Python_haq]$ python3 /home/huser/projects/Hello_World_Python_haq/start.py[SFW]2022-06-18 06:30:27.596[INFO](11414-device_checker.cpp:71)----- start DetectDevice ------[DEVICE]2022-06-18 06:30:27.618[INFO](11414-acl_mediaplugin.cpp:19)-----------load acl_C75 Media---------[DEVICE]2022-06-18 06:30:27.871[INFO](11414-acl_inferplugin.cpp:26)-----------load acl_C75 Infer---------[huser@studio-ide-679f67bb45-866xw Hello_World_Python_haq]$ cd /home/huser/projects/Hello_World_Python_haq[huser@studio-ide-679f67bb45-866xw Hello_World_Python_haq]$ python3 /home/huser/projects/Hello_World_Python_haq/start.py[SFW]2022-06-18 06:30:35.051[INFO](11501-device_checker.cpp:71)----- start DetectDevice ------[DEVICE]2022-06-18 06:30:35.073[INFO](11501-acl_mediaplugin.cpp:19)-----------load acl_C75 Media---------[DEVICE]2022-06-18 06:30:35.326[INFO](11501-acl_inferplugin.cpp:26)-----------load acl_C75 Infer---------Segmentation fault (core dumped)[huser@studio-ide-679f67bb45-866xw Hello_World_Python_haq]$ 麻烦帮忙看下如何解决,谢谢!截图如下:-----------------------------------------------------------------------
-
【功能模块】【操作步骤&问题现象】1、2、【截图信息】【日志信息】(可选,上传日志内容或者附件)
-
【功能模块】【操作步骤&问题现象】1、2、【截图信息】【日志信息】(可选,上传日志内容或者附件)
-
【功能模块】【操作步骤&问题现象】1、2、【截图信息】【日志信息】(可选,上传日志内容或者附件)
-
【功能模块】【操作步骤&问题现象】1、2、【截图信息】【日志信息】(可选,上传日志内容或者附件)
-
1、想要查看日志,提示需要更新固件至1.0.7以上,请问如何更新2、按照样例转换从AI Gallery上下载数据集训练并转换为.om文件后加载模型时提示错误:[DEVICE]2022-05-27 22:17:39.477[ERROR](2893-model_process.cpp:116)load model from file failed, ret = 507027[DEVICE]2022-05-27 22:17:39.477[ERROR](2893-acl_infer_impl.cpp:87)load model failed, model file is /home/huser/projects/ped_car_detect/model/convert-car-ped-detect.om[DEVICE]2022-05-27 22:17:39.477[INFO](2893-acl_infer_impl.cpp:170)load model /home/huser/projects/ped_car_detect/model/convert-car-ped-detect.om failed[DEVICE]2022-05-27 22:17:39.477[ERROR](2893-acl_infer_impl.cpp:62)Model: ACL resource init failed[DEVICE]2022-05-27 22:17:39.477[WARN](2893-model_process.cpp:299)no model had been loaded, unload failedTraceback (most recent call last): File "/home/huser/projects/ped_car_detect/start.py", line 17, in <module> main.run(work_path) File "./src/main/python/main.py", line 18, in run mask_model = hilens.Model(mask_model_path) File "/usr/lib64/python3.7/site-packages/hilens.py", line 140, in __init__ raise CreateError("failed to create Model")hilens.CreateError: 'failed to create Model'
-
在使用Hilens Studio开发完成后,运行可以显示输出画面。安装技能到Hilens Kit,显示successful 但启动技能后没有图像输出
-
获取您的EI红宝书:https://www.huaweicloud.com/ei/ AI测试是对基于AI的应用系统的测试;与任何系统一样,基于AI的系统具有功能性和非功能性需求。AI应用测试的主要流程包括场景分析,特征因子分析,数据构建,评测指标,自动化方案等AI应用测试AI测试任务分层AI应用测试框架关键角色AI开发工程师负责设计、开发实现、数据验收、自测、调优等工作数据工程师负责数据采集、数据清洗、数据整合、数据标注、数据质量检测等工作测试工程师负责测试数据采集、测试场景分析、测试方案、测试用例、测试策略、测试自动化、测试验收和评估等工作测试流程和活动① 结合需求描述,梳理典型应用场景,场景使用主体、特点等,将场景细化② 基于场景分析,分析影响Al模型识别率的特征因子,建立特征因子库。不同的AI场景对特征因子要求和复杂度不一样,比如CV应用场景的特征因子有拍摄因素(曝光、角度等)、环境因素(阴晴雨雪、背景等)、属性因素(人物年龄、肤色等)③ 基于应用场景、特征因子等进行数据集构建,包括不限于:数据类别、不同因子比例、环境因素、特定要求等④ 不同业务场景,关注不同的指标,评价的结果也不同,所以需要根据需求场景和侧重点,确定指标和相关定义。比如:有些业务求全,所以召回率优先;有些业务求准,所以准确率优先;有的业务因类别不均衡,要看单个类别的准确率;还有的业务内存非常敏感,所以对模型大小优先。⑤ 自动化批量测试及评测指标统计https://mp.weixin.qq.com/s?__biz=Mzg5Mjc4NjE1Nw==&mid=2247484542&idx=1&sn=4e6a77a15df21988fe72d41e133e8bdf&chksm=c03980fcf74e09eae416f1a5085ecba06804d9e17210e9a32f2706ebe201fbb8ceab4a6d13e8&token=70826191&lang=zh_CN#rd 云与数据- HCCDA-AI合集:https://mp.weixin.qq.com/mp/appmsgalbum?__biz=Mzg5Mjc4NjE1Nw==&action=getalbum&album_id=2398219468813811715&scene=173&from_msgid=2247483927&from_itemidx=1&count=3&nolastread=1#wechat_redirect**
-
【功能模块】【操作步骤&问题现象】1、2、【截图信息】【日志信息】(可选,上传日志内容或者附件)
-
获取您的EI红宝书:https://www.huaweicloud.com/ei/ 华为HiLens为端云协同多模态AI开发应用平台,供简单易用的开发框架、开箱即用的开发环境、丰富的AI技能市场和云上管理平台,接多种端侧计算设备,支持视觉及听觉AI应用开发、AI应用在线部署、海量设备管理等https://mp.weixin.qq.com/s?__biz=Mzg5Mjc4NjE1Nw==&mid=2247484541&idx=1&sn=8356331b4085c76c3a5139407ac59766&chksm=c03980fff74e09e907c12129a5daaa527d20111fa818c74d2acdd0a0e930d4dd8f4d00e0d792&token=1539735248&lang=zh_CN#rd 云与数据- HCCDA-AI合集:https://mp.weixin.qq.com/mp/appmsgalbum?__biz=Mzg5Mjc4NjE1Nw==&action=getalbum&album_id=2398219468813811715&scene=173&from_msgid=2247483927&from_itemidx=1&count=3&nolastread=1#wechat_redirect**
-
【功能模块】Atlas 200 HiLens Kit ssh注册失败,提示"The username or password is wrong."版本:2.2.200.011【操作步骤&问题现象】1、有线网络已连接,可ping通互联网2、三种注册途径都尝试了,都提示用户名或密码错误【截图信息】Euler:~ # hdactl register -u fengtao600 -d fengtao600 -n hilensPassword:Authenticating the account..."The username or password is wrong."Registration failure: Failed to authenticate the account.Euler:~ # timed out waiting for input: auto-logoutIES:/->Connection closing...Socket close.请各位专家帮忙诊断一下,多谢!
-
获取您的EI红宝书:https://www.huaweicloud.com/ei/ 华为云EI服务介绍:https://mp.weixin.qq.com/s/f1McTHORZ3OHLSGJHGrc-Q 01 图像识别API服务介绍 https://mp.weixin.qq.com/s/OdfsOTDkBpwLucHhipaXlg 02 图像搜索API服务介绍 https://mp.weixin.qq.com/s/wkelUMwPi7yrgEQfASgODQ 03 内容审核API服务介绍 https://mp.weixin.qq.com/s/HC_aZCfIIF1Ke8ofsUeijw 04 文字识别API服务介绍 https://mp.weixin.qq.com/s/1y6pG2LM83cs4OexHLTBjw 05 自然语言处理API服务介绍 https://mp.weixin.qq.com/s/C196lNKhiA4oeaelvh92hQ 06 语音交互API服务介绍 https://mp.weixin.qq.com/s/QeJ2e7XN9E-Rw3lFSKeA4Q 云与数据- HCCDA-AI合集:https://mp.weixin.qq.com/mp/appmsgalbum?__biz=Mzg5Mjc4NjE1Nw==&action=getalbum&album_id=2398219468813811715&scene=173&from_msgid=2247483927&from_itemidx=1&count=3&nolastread=1#wechat_redirect**
-
HiLens Kit,是基于hi3559,接口应该支持是很丰富的,怎么不把其他接口开放出来呢?例如GPIO不就可以驱动外设如伺服器,马达之类的,i2c再对接一些传感器等。这样可玩性大很多,也可以用在更多的场景。可能是因为成本的原因,但是这个增加不了几块成本好吧。ai端测很重要的。yd_18778538 发表于2022-05-14 21:50:17 2022-05-14 21:50:17 最后回复 yd_291289046 2022-05-18 15:47:201162 10
-
![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652462002460141317.png) 获取您的EI红宝书:https://www.huaweicloud.com/ei/ # 1.1 AI技术发展现状及技术挑战 ## 1.1.1 计算机视觉发展现状及技术挑战 ### 是什么? https://www.huaweicloud.com/product/image.html 计算机视觉是使计算机能理解采集设备采集的图像视频的一门学科。形象地说,就是给计算机安装上眼睛(照相机)和大脑(算法),让计算机能够感知环境。 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461416874478021.png) 如上图所示,真实的世界通过人眼成像,再传递给大脑进行理解,达到理解图像的目的;在机器视觉中,采集设备作为传感装置采集图像,将图像传递给计算机解读,最终达到计算机像人一样“读懂”图片的目的。 ### 能干什么? ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461565072415693.png) ### 有什么? ##### ① 视觉任务划分 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461621537644789.png) 中级视觉的物体检测包含2个任务:物体定位和分类 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461822933594109.png) 有时我们也会说计算机视觉有四大类任务:分类、定位、检测、分割。 ##### ② 视觉的三个层次 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461688891753994.png) 底层一般是像素级处理,比如亮度增强、直方图、直方图均化等; 中层即从中分析一些边缘、朝向、纹理等这些特征,可以对图片进行一个分割; 高层需要我们从中得到一些语义信息,比如图片中间是老虎,下边是沙滩,绿色的是草地,这可能是一个野外场景 ### 面临的挑战? ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461373371901001.png) ## 1.1.2 自然语言处理发展现状及技术挑战 ### 是什么? https://www.huaweicloud.com/product/nlpf.html 自然语言处理的处理主要包括两个部分:自然语言理解、自然语言生成 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461221554996108.png) ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652461261899121273.png) 自然语言理解(Natural Language Understanding,NLU) 使计算机理解自然语言(人类语言文字)等,重在理解。具体来说,就是理解语言、文本等,提取出有用的信息,用于下游的任务。如情感识别、意图识别、信息检索(包括个性化搜索和语义搜索,文本匹配等)、信息抽取(命名实体提取、关系抽取、事件抽取等)。 自然语言生成(Natural Language Generation, NLG) 提供结构化的数据、文本、图表、音频、视频等,生成人类可以理解的自然语言形式的文本。NLG又可以分为三大类,文本到文本(text-to-text),如翻译、摘要等;文本到其他(text-to-other),如文本生成图片;其他到文本(other-to-text),如视频生成文本。 ### 能干什么? 例: 智能问答 舆情分析 文本分类 实体抽取 摘要生成 AI写诗 机器翻译 内容审核 文本互译 ...... ### 面临的挑战? ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652460754955869960.png) ## 1.1.3 语音处理发展现状及技术挑战 ### 是什么? https://www.huaweicloud.com/product/rasr.html ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652460634874321882.png) ### 能干什么? 例: 实时字幕 会议记录 语音搜索 语音导航 有声阅读 ### 面临的挑战? ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652460728571303721.png) # 1.2 AI应用需求分析 ## 1.2.1 传统软件应用开发与AI应用开发对比 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459466560286171.png) ## 1.2.2 为什么需要进行需求分析 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652460021313211343.png) ### 1.2.2.1 AI应用开发需求分析步骤 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459658947449743.png) ### 案例:实例演练--智能人体测温监测系统 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459719675956096.png) ##### ① 需求背景 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459902567976285.png) ##### ② 需求价值 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459918708130176.png) ##### ③ 需求描述 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459926968703140.png) ##### ④ 问题抽象 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459936087416782.png) ##### ⑤ 可行性分析 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652459955955590397.png) 人工智能入门级开发者认证:https://edu.huaweicloud.com/certificationindex/developer/aaabf9760a3f4578aa620155e1fcae86 ![image.png](https://bbs-img.huaweicloud.com/data/forums/attachment/forum/20225/14/1652462051683666717.png)
上滑加载中
推荐直播
-
TinyEngine低代码引擎系列第2讲——向下扎根,向上生长,TinyEngine灵活构建个性化低代码平台
2024/11/14 周四 16:00-18:00
王老师 华为云前端开发工程师,TinyEngine开源负责人
王老师将从TinyEngine 的灵活定制能力出发,带大家了解隐藏在低代码背后的潜在挑战及突破思路,通过实践及运用,帮助大家贴近面向未来低代码产品。
回顾中 -
华为云AI入门课:AI发展趋势与华为愿景
2024/11/18 周一 18:20-20:20
Alex 华为云学堂技术讲师
本期直播旨在帮助开发者熟悉理解AI技术概念,AI发展趋势,AI实用化前景,了解熟悉未来主要技术栈,当前发展瓶颈等行业化知识。帮助开发者在AI领域快速构建知识体系,构建职业竞争力。
去报名 -
华为云软件开发生产线(CodeArts)10月新特性解读
2024/11/19 周二 19:00-20:00
苏柏亚培 华为云高级产品经理
不知道产品的最新特性?没法和产品团队建立直接的沟通?本期直播产品经理将为您解读华为云软件开发生产线10月发布的新特性,并在直播过程中为您答疑解惑。
去报名
热门标签