I've build a VR-System for Asterisk using Pocketsphinx. When testing the result I've encountered the phenomenon, that when I initially say a word which is recognized correctly, and in further runs don't say anything PS reiterates the last result (stating that the first result was said again, and again and so on). Why is that, or did I maybe set a config value wrong?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I cannot use vosk, because my system has to run on a very small embedded system with very closely defined limitations- therefore it has to be Pocketsphinx- so could you be a little bit more specific what you meant by more abput the code ?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
I've build a VR-System for Asterisk using Pocketsphinx. When testing the result I've encountered the phenomenon, that when I initially say a word which is recognized correctly, and in further runs don't say anything PS reiterates the last result (stating that the first result was said again, and again and so on). Why is that, or did I maybe set a config value wrong?
Its not about a config value, more about the code.
Overall, for asterisk the vosk-api will be much more accurate, I recommend you to try it.
I cannot use vosk, because my system has to run on a very small embedded system with very closely defined limitations- therefore it has to be Pocketsphinx- so could you be a little bit more specific what you meant by more abput the code ?
vosk is faster than pocketsphinx on compatible hardware
yes, but needs dependencies which I am not allowed to install