[Not for merge] Add full-chunk mode CTC decoding for models from WeNet #872
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Just for clarification: does "full-chunk decoding" mean "offline decoding"? |
Yes, you are right. The name full-chunk decoding is from WeNet, which is misleading at the first sight. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR shows that we can also use k2 for decoding with models from other frameworks.
For n-gram LM rescoring and attention decoder rescoring, it shares a lot of code with the following files and is very easy to implement.
It's for demonstration only and not ready for merge.
If others have a need for full-chunk batch decoding on GPU with models from WeNet or other frameworks, we can support that.