{"id":24176,"library":"openwakeword","title":"openWakeWord","description":"An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity. Current version is 0.6.0. Releases are periodic with enhancements and bug fixes.","status":"active","version":"0.6.0","language":"python","source_language":"en","source_url":"https://github.com/dscripka/openWakeWord","tags":["wake word","audio","speech","keyword spotting","machine learning"],"install":[{"cmd":"pip install openwakeword","lang":"bash","label":"Standard install"}],"dependencies":[],"imports":[{"note":"Direct import of module gives access to submodules, but the main class is OpenWakeWord.","wrong":"import openwakeword","symbol":"OpenWakeWord","correct":"from openwakeword import OpenWakeWord"},{"note":"Model class is used for loading and running wake word models.","symbol":"Model","correct":"from openwakeword.model import Model"}],"quickstart":{"code":"from openwakeword import OpenWakeWord\n\noww = OpenWakeWord()\naudios = []  # list of audio chunks (numpy arrays)\npredictions = oww.predict(audios)","lang":"python","description":"Initialize the wake word detector and run prediction on audio chunks."},"warnings":[{"fix":"Run `openwakeword.utils.download_models()` or `python -m openwakeword.utils.download_models` before inference.","message":"In v0.6.0, model files were removed from the package. You must download them separately using `openwakeword.utils.download_models()` or use the CLI.","severity":"breaking","affected_versions":">=0.6.0"},{"fix":"Install tensorflow or onnxruntime as needed, and specify framework='onnx' if you prefer ONNX.","message":"The default inference framework on Linux is tflite since v0.5.0. This may not be installed by default; ensure you have the necessary dependencies.","severity":"gotcha","affected_versions":">=0.5.0"},{"fix":"Convert audio to float32 and normalize before passing to predict.","message":"Input audio must be a list of 1D numpy arrays (dtype=float32) normalized to [-1, 1]. Passing raw integer PCM data will produce incorrect results.","severity":"gotcha","affected_versions":"all"}],"env_vars":null,"last_verified":"2026-05-01T00:00:00.000Z","next_check":"2026-07-30T00:00:00.000Z","problems":[{"fix":"Run `pip install openwakeword`.","cause":"openwakeword is not installed.","error":"ModuleNotFoundError: No module named 'openwakeword'"},{"fix":"Wrap your audio chunk in a list: `predict([audio_array])`.","cause":"Input to predict() is not a list of numpy arrays.","error":"ValueError: Audio frames must be a list of numpy arrays"},{"fix":"Run `from openwakeword.utils import download_models; download_models()` or use the CLI command.","cause":"Model files are missing (not downloaded). Since v0.6.0, models are no longer bundled.","error":"FileNotFoundError: [Errno 2] No such file or directory: '.../models/alexa.onnx'"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}