STT
STT copied to clipboard
Feature request: option to only allow sentences which occur in the language model
An option to only allow sentences which occur in the language model would be very helpful.
For example, the language model contains this:
flap one gear down
Currently STT can recognize audio as "gear one", which does not make sense in a voice command application. It would be great if an option is available to look for a better alternative and only allow one of the exact sentences from the language model with the words in the same order.
Edit: As a hack, words in sentences can be forced to be recognized in the correct order by removing the spaces. So the the language model in the example above would be like this;
flapone geardown
This would only work in a command execution scenario though.