Winfried / Wakeword-Computer Public
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

Espressif ESP-EYE (ESP32 240MHz)

100 ms

4096 kB

4096 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

98%
mfe-conv1d-a82
PERFORMANCE
LATENCY
97 ms of 100 ms
RAM
16 kB of 4096 kB
ROM
70 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 98%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

2/25/2025, 5:36:19 PM

96%
mfe-conv1d-cf8
PERFORMANCE
LATENCY
90 ms of 100 ms
RAM
16 kB of 4096 kB
ROM
70 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 96%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

2/25/2025, 5:39:55 PM

94%
mfe-conv1d-8b5
PERFORMANCE
LATENCY
173 ms of 100 ms
Exceeds target by 73 ms
RAM
17 kB of 4096 kB
ROM
35 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 94%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

2/25/2025, 5:46:05 PM

93%
mfe-conv1d-6a5
PERFORMANCE
LATENCY
124 ms of 100 ms
Exceeds target by 24 ms
RAM
16 kB of 4096 kB
ROM
43 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 93%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

2/25/2025, 5:54:08 PM

92%
mfe-conv1d-fb7
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
5 kB of 4096 kB
ROM
35 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 92%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

2/25/2025, 5:45:45 PM

90%
mfe-conv1d-691
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
5 kB of 4096 kB
ROM
35 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 90%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

2/25/2025, 5:52:51 PM

88%
mfe-conv2d-1e2
PERFORMANCE
LATENCY
47 ms of 100 ms
RAM
10 kB of 4096 kB
ROM
38 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 88%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

2/25/2025, 5:53:09 PM

87%
mfcc-conv1d-3c4
PERFORMANCE
LATENCY
316 ms of 100 ms
Exceeds target by 216 ms
RAM
19 kB of 4096 kB
ROM
41 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 40

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

2/25/2025, 5:43:39 PM

87%
mfcc-conv1d-595
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
4 kB of 4096 kB
ROM
34 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

2/25/2025, 5:43:23 PM

87%
mfcc-conv1d-371
PERFORMANCE
LATENCY
242 ms of 100 ms
Exceeds target by 142 ms
RAM
19 kB of 4096 kB
ROM
41 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

2/25/2025, 5:37:28 PM

87%
mfcc-conv1d-942
PERFORMANCE
LATENCY
305 ms of 100 ms
Exceeds target by 205 ms
RAM
19 kB of 4096 kB
ROM
34 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

2/25/2025, 5:39:34 PM

87%
mfcc-conv1d-4c4
PERFORMANCE
LATENCY
409 ms of 100 ms
Exceeds target by 309 ms
RAM
22 kB of 4096 kB
ROM
69 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

2/25/2025, 5:37:01 PM

86%
mfcc-conv1d-340
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
6 kB of 4096 kB
ROM
42 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 86%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

2/25/2025, 5:45:31 PM

86%
mfcc-conv1d-cab
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
4 kB of 4096 kB
ROM
34 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 86%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

2/25/2025, 5:42:46 PM

85%
mfcc-conv1d-6d1
PERFORMANCE
LATENCY
10 ms of 100 ms
RAM
5 kB of 4096 kB
ROM
42 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 85%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

2/25/2025, 5:47:34 PM