Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

any way to increase reliability for recognizing individual letters and numbers? #445

Open
vesper8 opened this issue Jan 30, 2022 · 1 comment

Comments

@vesper8
Copy link

vesper8 commented Jan 30, 2022

I'm using annyang to input chess moves and I'm finding it very challenging to have it correctly recognize commands such as "D 2" and "B 2", "E 2" and so on.

Is there a browser in particular that might do a better job than others? Clearly my own voice and pronunciation is a factor in this, I'm just finding it borderline unfeasible at all with how often it incorrectly understands my input, as simple as those inputs are meant to be (64 sounds ranging from "A 1" to "H 8"

@limury
Copy link
Contributor

limury commented Aug 10, 2022

Hi! So different browsers will definitely perform differently since Annyang uses the Web Speech API for processing, and the algorithm used by the Web Speech API is different across browsers. However, I unfortunately do not think that there are any reports on what browser is the best and the worst. Also since the functionality is very niche, your best bet is probably just to test them out yourself.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants