Error while compiling

Question/Issue: I am trying out the “Responding to your voice - Syntiant - RC Commands” tutorial but with new keywords, “hello” and “bye” . I am using the Syntiant TinyML board I was able to train my model and deploy it. I followed the steps as given here: On your Syntiant TinyML Board - Edge Impulse Documentation.
I updated the .ino file with the new keywords and updated the model parameters folder. I got this error while compiling - firmware-syntiant-tinyml\src\model-parameters\model_variables.h:52:1: error: too many initializers for 'const ei_model_performance_calibration_t
Can somebody help?

Project ID:

Context/Use case: Voice Commands

Hi @yogitha.pikkili,

Indeed this is linked to our new performance calibration feature. We will update the SDK in the github repo soon. In the meantime, you can just comment the following lines in the src/model-parameters/model_variables.h file:

const ei_model_performance_calibration_t ei_calibration = {
    1, /* integer version number */
    false, /* has configured performance calibration */
    (int32_t)(EI_CLASSIFIER_RAW_SAMPLE_COUNT / ((EI_CLASSIFIER_FREQUENCY > 0) ? EI_CLASSIFIER_FREQUENCY : 1)) * 1000, /* Model window */
    0.8f, /* Default threshold */
    (int32_t)(EI_CLASSIFIER_RAW_SAMPLE_COUNT / ((EI_CLASSIFIER_FREQUENCY > 0) ? EI_CLASSIFIER_FREQUENCY : 1)) * 500, /* Half of model window */
    0   /* Don't use flags */
};

Aurelien

Hi @yogitha.pikkili,

Thanks for notifying us. I’ve updated the Syntiant TinyML repo. GitHub - edgeimpulse/firmware-syntiant-tinyml: Edge Impulse firmware for Syntiant TinyML board

Regards,
Arjan

Hi @aurel and @Arjan! Thank you for letting me know! Commenting out the lines worked. I was able to compile it successfully! Thanks again :slight_smile: