The EON Tuner helps you quickly run hyper-parameter sweeps that explore different pre-processing + model architectures optimized for your defined objectives. Clone this project to use the EON Tuner.
Target
Run #2
Sony Spresense (Cortex-M4F 156MHz)
100 ms
1536 kB
8192 kB
Filters
Status
DSP type
Model type
View
Data set
Variant
Sort
General
F1-score
Precision
Recall
Run #2 (Jul 09 2025, 06:20:02, finished)
mfcc-bdf
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8192 kB
Unused
TIME-SERIES INPUT
3000 ms
|
3000 ms
|
Enabled
MFCC
| Parameter | Value |
|---|---|
| pre_cof | 0.98 |
| win_size | 101 |
| dspBlockId | 41 |
| fft_length | 256 |
| num_filters | 40 |
| frame_length | 0.05 |
| num_cepstral | 13 |
| low_frequency | 0 |
| high_frequency | 0 |
| frame_stride_pct | 0.5 |
KERAS
| Parameter | Value |
|---|---|
| dropout | 0.25 |
| dimension | conv1d |
| convLayers | 2 |
| learningRate | 0.005 |
| trainingCycles | 100 |
| convBaseFilters | 16 |
| augmentationPolicySpectrogram | [object Object] |
1
mfe-37d
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8192 kB
Unused
TIME-SERIES INPUT
1000 ms
|
500 ms
|
Enabled
MFE
| Parameter | Value |
|---|---|
| dspBlockId | 36 |
KERAS-TRANSFER-KWS
| Parameter | Value |
|---|---|
| model | transfer_kws_mobilenetv1_a1_d100 |
| learningRate | 0.01 |
| trainingCycles | 30 |
0
Training output
Hide
Click 'Run EON Tuner' to begin
