4verburga / disputa-wordpack Public
Target: Cortex-M4F 80MHz 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)
576
1000
Sample frequency (Hz)
16000
16000
Sample name Expected outcome Length Accuracy Result
unknown_m_028 PELEA 876ms 100% PELEA
Show classification Show in data acquisition Show in feature explorer
unknown_m_023 PELEA 716ms 100% PELEA
Show classification Show in data acquisition Show in feature explorer
unknown_m_010 PELEA 576ms 100% PELEA
Show classification Show in data acquisition Show in feature explorer
unknown_m_006 PELEA 608ms 100% PELEA
Show classification Show in data acquisition Show in feature explorer
unknown_f_031 PELEA 972ms 100% PELEA
Show classification Show in data acquisition Show in feature explorer
unknown_m_030 DISPUTA 1s 0% uncertain
Show classification Show in data acquisition Show in feature explorer
unknown_m_025 DISPUTA 684ms 100% DISPUTA
Show classification Show in data acquisition Show in feature explorer
unknown_m_003 DISPUTA 588ms 100% DISPUTA
Show classification Show in data acquisition Show in feature explorer
unknown_m_002 DISPUTA 908ms 100% DISPUTA
Show classification Show in data acquisition Show in feature explorer
melani_f_022 DISPUTA 864ms 100% DISPUTA
Show classification Show in data acquisition Show in feature explorer
melani_f_021 CONFLICTO 876ms 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
melani_f_018 CONFLICTO 940ms 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
melani_f_012 CONFLICTO 940ms 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
melani_f_008 CONFLICTO 1s 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
melani_f_006 CONFLICTO 940ms 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
ever_m_010 CONFLICTO 876ms 100% CONFLICTO
Show classification Show in data acquisition Show in feature explorer
ever_m_005 CONFLICTO 812ms 100% CONFLICTO
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
94.12%

Metrics for Transfer learning (Keyword Spotting)

Metric Value
Weighted average Precision 0.95
Weighted average Recall 0.94
Weighted average F1 score 0.94

Confusion matrix

Loading...

Feature explorer

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