Closed summer1704 closed 1 year ago
Sure, if you see a word "help" in recognition results you act accordingly. Thats it!
Same as #107
Can I use this model to trigger an action immediately after the keyword has uttered without having to wait for the entire speech to get transcribed and then do the trigger action.
Sure, analyze partial results
I am planning to detect single keyword with a good accuracy in any sentence. For example while someone is speaking, if they say the keyword "help" at any given time, it triggers an action. Is there any way that I can approach this problem using vosk-api