Hi,
I already use another tool for Hotword Detection (Raven)
With this tool, everything works. But it doesn’t cover all my nneds; so I woule like to give Porcupine a try.
I’m also able to record my voice with “arecord” and then listen to the recorded file with “aplay”
Is it sufficient to consider the microphone hardware/setup part is OK ? I can do other tests if you wish
I also created an issue on the picovoice github and there is the answer I got:
we don’t support this platform. we do support respeaker microphone arrays from respeaker.
I’m a little lost TBH.
Is my problem related to an error on my side or is the Repeaker Core v2 just not supported by Porcupine ?
Is there someone that could confirm he got Porcupine working on this platform ?
Seems like in the Readme of the porcupine github repo it states that it supports following platform:
cross-platform:
Arm Cortex-M, STM32, Arduino, and i.MX RT
Raspberry Pi, NVIDIA Jetson Nano, and BeagleBone
Android and iOS
Chrome, Safari, Firefox, and Edge
Linux (x86_64), macOS (x86_64, arm64), and Windows (x86_64)
where our ReSpeaker Core v2.0 is based on Rockchip RK3229, a quad-core ARM Cortex A7 platform. So I guess this processor has not been tested with the picovoice team and that’s why they state that they do not support this platform.
If you willing to give it try that will be great, I would suggest to show some error logs so that the people who are also interest can debugging with you together.
Thanks