demsking/oremi-ohunerin repository overview

⁠Oremi Ohunerin

Oremi Ohunerin is the real-time audio detection component of the Oremi Personal Assistant project, operating as a websocket server proficient in identifying environmental sounds and the specific wake word to activate Oremi.

Leveraging cutting-edge technologies such as Tensorflow YAMNet for comprehensive audio detection and PocketSphinx for precise wake word identification, this component ensures accurate recognition of various sound categories, including but not limited to shouts, laughter, crying, and more.

Derived from the Yoruba term "ohun erin," meaning "sound detection," Ohunerin embodies the essence of its function, facilitating seamless integration of auditory cues into the Oremi ecosystem, thus enhancing user experience and interaction.

Usage & Documentation⁠