Cramredan / Tutorial Audio Public
Target: Arduino Portenta H7 (Cortex-M7 480MHz) Clone this project

Test data

Set thresholds
Model variants
Test 'Unoptimized (float32)' model Test 'Quantized (int8)' model
Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.

Apply filters

Sample length (ms)
5056
60566
Sample frequency (Hz)
16000
48000
Sample name Expected outcome Length Accuracy Result
testing.745715gp testing 5s
Show classification Show in data acquisition Show in feature explorer
testing.744v338u testing 5s
Show classification Show in data acquisition Show in feature explorer
testing.744tvqqe testing 5s
Show classification Show in data acquisition Show in feature explorer
testing.744tsd2v testing 5s
Show classification Show in data acquisition Show in feature explorer
drops_16-09-2026 15-59_normalized-20dB drop 1m 1s 100% 199 drop
Show classification Show in data acquisition Show in feature explorer
drops_16-09-2026 16-02_normalized-20dB drop 1m 0s 100% 199 drop
Show classification Show in data acquisition Show in feature explorer
noise12.uvcljru.wav noise 1m 0s 100% 197 noise
Show classification Show in data acquisition Show in feature explorer
faucet1.v1m71av.wav faucet 1m 0s 100% 197 faucet
Show classification Show in data acquisition Show in feature explorer
Filter yielded no results, click to adjust the filter

Model testing output

Results

Model version:
Accuracy
100.00%

Metrics for NN Classifier

Metric Value
Area under ROC Curve 1.00
Weighted average Precision 1.00
Weighted average Recall 1.00
Weighted average F1 score 1.00

Confusion matrix

Loading...

Feature explorer

Loading...
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy