Diana_Laura_FD / Keywordpublic Public
Target: SAMSUNG Clone this project
Experiments EON Tuner
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

SAMSUNG

100 ms

8388608 kB

268435456 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

100%
mfe-mobilenetv2-2e4
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
236 kB of 8388608 kB
ROM
526 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.02 | 0.01 | 40

ACCURACY (OVERALL)
TRANSFER LEARNING (KEYWORD SPOTTING)

0.01 | 30 | 100%

MobileNetV2 0.35
0 | 0.1

0 6/14/2025, 4:49:53 PM

99%
mfcc-conv1d-e12
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
23 kB of 8388608 kB
ROM
67 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 99%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

0 6/14/2025, 4:29:53 PM

99%
mfe-conv1d-1a5
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
17 kB of 8388608 kB
ROM
68 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 99%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

0 6/14/2025, 4:29:55 PM

97%
mfcc-conv2d-f62
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
35 kB of 8388608 kB
ROM
41 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.016 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 97%

Type Filters Kernel Rate
Data augmentation
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

0 6/14/2025, 4:35:58 PM

92%
mfe-mobilenetv1-f1f
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
57 kB of 8388608 kB
ROM
97 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.02 | 0.01 | 40

ACCURACY (OVERALL)
TRANSFER LEARNING (KEYWORD SPOTTING)

0.01 | 30 | 92%

MobileNetV1 0.1
0 | 0.1

1 6/14/2025, 5:10:52 PM

62%
mfe-conv2d-f95
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
64 kB of 8388608 kB
ROM
64 kB of 268435456 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 62%

Type Filters Kernel Rate
Data augmentation
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

0 6/14/2025, 4:54:49 PM

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