Carlos / HelloAmbiq Public

Target: Cortex-M4F 80MHz Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

HelloAmbiq

Keyword spotting

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (1,682 samples)

View all

unknown.2aca1e72_nohash_4

ID: 143094603

Label: unknown

Sample length: 1s

unknown.ee1d8d49_nohash_4

ID: 143093685

Label: unknown

Sample length: 1s

unknown.f6581345_nohash_0

ID: 143093647

Label: unknown

Sample length: 1s

unknown.33903159_nohash_2

ID: 143094551

Label: unknown

Sample length: 1s

unknown.2fcb6397_nohash_1

ID: 143094589

Label: unknown

Sample length: 1s

hello.3g55b3no.s3

ID: 143093512

Label: hello

Sample length: 1s

unknown.01648c51_nohash_0

ID: 143094791

Label: unknown

Sample length: 1s

hello.3g53doeu.s6

ID: 143093601

Label: hello

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

94.4%

Test set

94.8%

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

543 ms.

Peak RAM usage

45.5K

Flash usage

123.7K

Run this model

On any device

Clone project

Dataset summary

Data collected

28m 45s

Sensor

audio @ 16KHz

Labels

hello, unknown

Project info

Project ID	149224
Project version	1
License	Apache 2.0
No. of views	61,515
No. of clones	4