precise-lite for both amd64 and aarch64
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
Olivier 'reivilibre' cbe8865db0 Upgrade to TF 2.7.1 with Aarch64 wheels to hopefully make this usable on R0 1 month ago
data Refine .gitignores 4 years ago
precise_lite add wrapped stream (do not open new pyaudio stream) 1 year ago
runner add wrapped stream (do not open new pyaudio stream) 1 year ago
.gitignore Add pytest cache to .gitignore 4 years ago
LICENSE Change license to Apache 2.0 5 years ago
README.md Upgrade to TF 2.7.1 with Aarch64 wheels to hopefully make this usable on R0 1 month ago
requirements.txt tflite edition #0 1 year ago
setup.py Upgrade to TF 2.7.1 with Aarch64 wheels to hopefully make this usable on R0 1 month ago
setup.sh Modded the bash and requirements 2 years ago

README.md

rei's fork of Precise-Lite

  • To install, use pip3 install . ./runner for both the engine and runner. All training scripts are included.
    • Use an up-to-date pip to avoid installing conflicting requirements!
  • This fork supports Aarch64 using the tensorflow_aarch64 packages.

Mycroft Precise-Lite

A lightweight, simple-to-use, RNN wake word listener.

Precise is a wake word listener. The software monitors an audio stream ( usually a microphone ) and when it recognizes a specific phrase it triggers an event. For example, at Mycroft AI the team has trained Precise to recognize the phrase "Hey, Mycroft". When the software recognizes this phrase it puts the rest of Mycroft's software into command mode and waits for a command from the person using the device. Mycroft Precise is fully open source and can be trined to recognize anything from a name to a cough.

Usage

precise-lite-listen my_model_file.net

To convert it into tflite run

precise-lite-convert my_model_file.net

And you can run then tflite

precise-lite-listen my_model_file.tflite