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

Kaldi is too fast #36

Open
kendonB opened this issue Sep 10, 2020 · 8 comments
Open

Kaldi is too fast #36

kendonB opened this issue Sep 10, 2020 · 8 comments

Comments

@kendonB
Copy link

kendonB commented Sep 10, 2020

I know that this is a very good problem to have! Several times (at least since the last update) I have found Kaldi will interpret my speech well before I'm done uttering a phrase. For example, in Caster we can say "go line sixteen" to navigate to line sixteen.

Sometimes the system will interpret this as "go line six" then interpret "teen" as something completely different as Kaldi almost always trys to interpret any real speech. For me, I get "teen" interpreted as "doon" (my word for page down), for example.

Is there a setting we can tweak to prevent this from happening?

@dwks
Copy link

dwks commented Sep 11, 2020

Try vad_padding_end_ms in kaldi_module_loader_plus.py. I myself have set it to 200ms up from 100 to avoid this problem.

@daanzu
Copy link
Owner

daanzu commented Sep 14, 2020

Yeah, adjusting vad_padding_end_ms will help. Perhaps I was over aggressive in setting the default to 150. Also, you can try adjusting vad_aggressiveness from the default 3 down to 2 or 1, which should make it less likely to cut off quiet sounds. I should probably have a section for "parameters you will likely want to adjust for preference" like this.

@kendonB
Copy link
Author

kendonB commented Sep 23, 2020

@daanzu where do these parameters sit in the kaldi_model folder? Or are those settings fixed in the releases?

@daanzu
Copy link
Owner

daanzu commented Sep 24, 2020

They are engine parameters for dragonfly, so they are set in the get_engine() call, which should be in your loader. So something like this: get_engine('kaldi', vad_padding_end_ms=200). How are you running things?

@kendonB
Copy link
Author

kendonB commented Sep 26, 2020

@LexiconCode
Copy link

Yep it's something I've been trying to think how the best implement.

@daanzu
Copy link
Owner

daanzu commented Sep 30, 2020

dictation-toolbox/dragonfly#302 may help until Caster has a good way to pass engine parameters.

@LexiconCode
Copy link

LexiconCode commented Dec 3, 2020

Just modify the bat file for now python -m dragonfly load _*.py --engine kaldi --no-recobs-messages --engine-options "model_dir=kaldi_model, vad_padding_end_ms=300"

List of kaldi engine parameters for configuration.

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

4 participants