Skip to content

Use TTS to create synthetic audio data for hotword detection

Notifications You must be signed in to change notification settings

yodakohl/HotwordSynth

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

HotwordSynth

Use TTS to create synthetic audio data for hotword detection

Poor mans way to get audio samples for a specific hotword. This uses different free linux TTS systems to generate a range of audio samples for hotword detection.

Don't expect this to work very well in production, as due to the limited number of voices and low variety this tends to overfit quickly

About

Use TTS to create synthetic audio data for hotword detection

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages