tensorflow-models/speech-commands easiest example

...





Original example by @tafsiri at https://glitch.com/~tfjs-speech-commands


This website is able to understand 4 speech commands, it works best if you use headphones or an external speaker:
"up", "down", "left", "right",

Still testing the full 18 commands:
need to set vocabulary: '18w' for the full set.
0, 1, 2, 3, 4, 5, 6,7 8, 9,
"go", "stop", "yes", "no",
"unknown word" , "background noise".