Repository navigation
WO52 M3+M5: corpus pins + conformance fixtures - #296
Merged
Merged
Conversation
added 3 commits
October 18, 2026 08:32
Stream-hashed all seven splits (no local copies): urd-dia 573,130/ 11,940, fas-dia 445,869/9,288 (the docs split, sha 67513aa1), qcri- wiki 32,834 article-lines, urd-g2p 609,580/12,699. Corpora are now content-addressed: a rebuild that changes a byte fails the registry.
The frozen-fixture contract for every IMF runtime: a vectors file pins (model, single-row-greedy decode mode, src -> exact output); runtimes must reproduce outputs byte-exactly or the change does not merge. Includes the reference ONNX decoder (byt5 byte+3 with trailing EOS — the WO51 single-row contract) and the isxml conformance verb. 4 tests written first; suite 234 green.
12 byte-exact vectors generated with the reference decoder from the shipped fp16 zip (first 12 rows of urd-dia#test); CONFORMANCE.md records the single-row-greedy decode contract and the WO51 rule that maskless batched decode is outside it.
ronaldtse
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.