Metadata-Version: 2.1
Name: openwakeword-pruned
Version: 0.5.1
Summary: A pruned version of the open source framework 'openwakeword' by David Scripka
Home-page: https://github.com/siranshen/openWakeWord-Pruned
Author: David Scripka, Siran Shen
Project-URL: Homepage, https://github.com/siranshen/openWakeWord-Pruned
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: onnxruntime<2,>=1.10.0
Requires-Dist: tflite-runtime<3,>=2.8.0; platform_system == "Linux"
Requires-Dist: tqdm<5.0,>=4.0
Requires-Dist: requests<3,>=2.0
Provides-Extra: test
Requires-Dist: pytest<8,>=7.2.0; extra == "test"
Requires-Dist: pytest-cov<3,>=2.10.1; extra == "test"
Requires-Dist: pytest-flake8<2,>=1.1.1; extra == "test"
Requires-Dist: flake8<4.1,>=4.0; extra == "test"
Requires-Dist: pytest-mypy<1,>=0.10.0; extra == "test"
Requires-Dist: types-requests; extra == "test"
Requires-Dist: types-PyYAML; extra == "test"
Requires-Dist: mock<6,>=5.1; extra == "test"
Requires-Dist: types-mock<6,>=5.1; extra == "test"
Requires-Dist: types-requests<3,>=2.0; extra == "test"

# Intro

openWakeWord is an open-source wakeword library that can be used to create voice-enabled applications and interfaces.
It includes pre-trained models for common words & phrases that work well in real-world environments.

This is forked repo. See [original repo](https://github.com/dscripka/openWakeWord) for details.

# Changes in this fork

This fork prunes code related to custom model training and verification.
By avoiding importing modules related to custom models such as `sklearn`, it saves ~33MB of memory.
It proves to be useful on memory constrained devices, such as the Raspberry Pi Zero series.

# Installation

Run:
```commandline
pip install openwakeword-pruned
```
Check out other configs in the [original repo](https://github.com/dscripka/openWakeWord#installation).
