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

On the fly decoding support #43

Open
StevenZYj opened this issue Sep 13, 2021 · 1 comment
Open

On the fly decoding support #43

StevenZYj opened this issue Sep 13, 2021 · 1 comment

Comments

@StevenZYj
Copy link

Hi, i'm new here. First thanks to this project. Though early, it looks awesome.
I go through the current recipes and find that they are all based on ctc topology. I wonder if the current version supports on the fly decoding with aed model? Specifically, i mean aed model outputing phoneme based score and wfst based LG model dynamically computing corresponding word based score.

@csukuangfj
Copy link
Collaborator

I wonder if the current version supports on the fly decoding with aed model? Specifically, i mean aed model outputing phoneme based score and wfst based LG model dynamically computing corresponding word based score.

We are doing it in the opposite direction:

  • (1) The attention encoder output is used in CTC decoding
  • (2) We extract n-paths from the resulting lattice obtained from CTC decoding
  • (3) An n-gram LM and the attention decoder are used to rescore those n-paths.

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