ovos-ww-plugin-wakeforge

An OVOS wake-word plugin for custom models trained with wakeforge.

Wakeforge trains a wake-word detector from a single phrase and exports a two-file ONNX pipeline: a feature extractor and a classifier head. This plugin loads that pipeline and runs it as an always-on hotword engine. The runtime uses onnxruntime and numpy only. It does not need PyTorch.

Install

pip install ovos-ww-plugin-wakeforge

Train a model

pip install wakeforge
wakeforge-quickstart "hey jarvis" ./hey_jarvis
# → ./hey_jarvis/best_f1_featurizer.onnx  +  ./hey_jarvis/best_f1.onnx

Configure

In mycroft.conf, point a hotword at the two ONNX files. Use local paths or URLs.

{
  "listener": {
    "wake_word": "hey_jarvis"
  },
  "hotwords": {
    "hey_jarvis": {
      "module": "ovos-ww-plugin-wakeforge",
      "listen": true,
      "featurizer": "~/hey_jarvis/best_f1_featurizer.onnx",
      "model": "~/hey_jarvis/best_f1.onnx",
      "threshold": 0.5
    }
  }
}

Config keys

key	default	description
`featurizer`	— (required)	feature-extractor ONNX (path or URL)
`model`	— (required)	classifier-head ONNX (path or URL)
`vad`	none	optional VAD ONNX for an extra channel
`threshold`	`0.5`	detection threshold
`smoothing`	`ema`	`ema` \| `mean` \| `max`
`patience`	`3`	consecutive above-threshold frames to fire
`debounce_sec`	`1.0`	minimum seconds between triggers
`window_size`	`5`	smoother rolling window (mean/max)
`ema_alpha`	`0.3`	EMA responsiveness
`block_ms`	`80`	audio is scored in blocks of this length whatever chunk size the listener sends, so patience counts time and the featurizer always gets a full block
`streaming`	`false`	use the stateful streaming (GRU) head
`gru_window`	`100`	window the streaming head was exported with
`hidden_dim`	`128`	GRU hidden size of the streaming head

URL models are cached under ${XDG_DATA_HOME}/wakeforge/.

TigreGotico/wakeforge trains the ONNX models this plugin loads.
OpenVoiceOS/ovos-plugin-manager loads and manages this plugin alongside other STT, TTS, and wake-word plugins.
OpenVoiceOS/ovos-ww-plugin-precise-onnx is a sibling wake-word plugin that runs Precise models through ONNX.

Credits

Developed by TigreGótico for OpenVoiceOS.

This project was funded through the NGI0 Commons Fund, a fund established by NLnet with financial support from the European Commission's Next Generation Internet programme, under the aegis of DG Communications Networks, Content and Technology under grant agreement No 101135429.

License

Apache-2.0

Metadata

Release files for ovos-ww-plugin-wakeforge 0.0.4a1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ovos-ww-plugin-wakeforge 0.0.4a1
File	Size	Uploaded
ovos_ww_plugin_wakeforge-0.0.4a1.tar.gz	18.4 kB	Sep 18, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for ovos-ww-plugin-wakeforge 0.0.4a1
File	Interpreter	ABI	Platform	Reset
ovos_ww_plugin_wakeforge-0.0.4a1-py3-none-any.whl 16.1 kB Sep 18, 2026	Python 3	none	any	Details

Total release size: 34.5 kB

Release files / ovos_ww_plugin_wakeforge-0.0.4a1.tar.gz

Download URL	ovos_ww_plugin_wakeforge-0.0.4a1.tar.gz
Size	18.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`b33aea34c940d7cb2679977ce75742f48802c31c3b10d710ae2fcade159cfdbb`
BLAKE2b-256 checksum How to use checksums	`7eae3f7221932b88767ba518686962b0d8cc722aa2ea8bea4cb89396cbc57a11`
Upload date	Sep 18, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Release files / ovos_ww_plugin_wakeforge-0.0.4a1-py3-none-any.whl

Download URL	ovos_ww_plugin_wakeforge-0.0.4a1-py3-none-any.whl
Size	16.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`5891607bed22aacd3246a6019d0b9acbbd22ec3cda0ce3c60f2684cc462d679d`
BLAKE2b-256 checksum How to use checksums	`a08e64b977894097329300c482087b1dfd8dbf85b5edddb92f6febae97fa6bfa`
Upload date	Sep 18, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`