Multicharacter Token Support #193
Open
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
|
Hi @SeanNaren , could you please review the PR? Thanks, Peter. |
|
@SeanNaren please merge this branch, this is a really needed feature |
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Outdated suggestions cannot be applied.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.
The CTC decoder might perform worse when using multicharacter tokens (e.g., BPEs). This issue is mentioned in #173.
The reason is that the implementation sets
is_character_basedinScorertofalsebecause the tokens in LM's dictionary have more than one character. Whenis_character_basedisfalsetheScorercreates an FST based on malformed transitions (add_word_to_dictionary()breaks the tokens/words in LM's dictionary to characters and not to tokens).This pull request adds an option
is_token_basedthat indicates that the vocabulary consists of custom (multicharacter) tokens.