Repository navigation
docs: WO68 — attempt 3: expansion replicates the teacher (tie) - #399
Merged
Merged
Conversation
… (27.08 vs 27.42)
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Attempt 3 (latn-convention weak labels, 74,992 words) verdict: student 27.079% CER vs teacher 27.417% on the identical 895-row translit test split — nominally EXPANSION_PAYS, but the delta is within noise and the teacher's score reproduces its published 27.42 exactly. Weak-label expansion replicates the teacher rather than exceeding it; the CER<15 B7 target still hinges on new gold (SEAlang / Chuon Nath IPA, owner-held).