Hi,
I am facing an error while demo_speech_recognition application is being compiled for the centos.
The error occurs when speech_library_app.cpp.o is being compiled.
I have attached the screenshot for reference.
Can anyone please let me know the reason for this error and how to resolve it?
Thanks in advance
链接已复制
Hi Kushagra,
Thank you for waiting, and our apologies for the delay.
We were able to build demo_speech_recognition for CentOS without any errors.
As such, we would like to check if you have all the prerequisites installed, as per
They are:
- CentOS 7.6 64-bit
- GCC 4.8.5 (for CentOS 7.6)
- CMake version 3.10 or higher
We would also like to know the following:
- Which OpenVINO version have you installed (and from what source)?
- Are you able to run the verification demos (demo_squeezenet_download_convert_run.sh or demo_security_barrier_camera.sh) without errors?
Regards,
Munesh
Hi,
I checked the pre-requisites and they match the requirements for openvino.
The version being used is: 2020.4.287
We were able to run other demos as well.
Please note we are not trying to rung the sample application.
We try to rung the demo present under "deployment_tools" directory for speech recognition which is supposed to download the application and run a demo.
It is that one that causes an error.
Is it possible that it can be checked.
Thanks in advance.
Hi Kushagra,
We've replicated your issue, were able to run the ./demo_speech_recognition.sh script under deployment_tools/demos.
I would suggest you try running the same demo with OpenVINO 2021.2. If you still face the same issue then, please furnish us with the entire output when running the script.
Regards,
Munesh
Hi,
Could please check the 2021.2 version. I downloaded it and it does not have the speech recognition demo.
I have attached the screenshot for reference.
Thanks in advance.
Best Regards,
Kushagra
Hi Kushagra,
Apologies for the delay and thank you for waiting.
For OpenVINO toolkit built from source, the Developer team have acknowledged this case as a bug and they are currently working on a fix. Meanwhile, as a workaround you could use Intel® Distribution of OpenVINO™ Toolkit instead of open source version.
Regards,
Munesh
Hi Kushagra,
With regards to the speech recognition demo in open source OpenVINO, the script uses 3rd party libraries and currently we haven't got an approval to use this code in the open source version.
As such, the speech recognition demo is so far available in Intel binary releases only for Ubuntu 18.04 & Windows.
We have a note mentioning this in the following page:
"Intel® distributions of OpenVINO™ toolkit for Linux OS and Windows OS provide a set of libraries and demos to demonstrate end-to-end speech recognition, as well as new acoustic and language models that can work with these demos."
Regards,
Munesh