feat(models): add Roman Hinglish Whisper model - #46
Merged
Conversation
✅ Deploy Preview for voca-gateway canceled.
|
There was a problem hiding this comment.
Mr-Sunglasses has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
There was a problem hiding this comment.
Mr-Sunglasses has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
Mr-Sunglasses
force-pushed
the
feat/hinglish-roman
branch
from
September 3, 2026 18:39
9300497 to
2c5eada
Compare
There was a problem hiding this comment.
Mr-Sunglasses has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
VocaPhone PR #218 adds an opt-in Roman Hinglish output mode backed by
Oriserve/Whisper-Hindi2Hinglish-Apex. The gateway catalog does not currently expose that model, and passing itshinglish_romanoutput contract directly to whisper.cpp would use an invalid decoder language token.Summary
ggml-apex-hinglish-q5_0.binGGML model from the PR's immutable third-party conversion, with its SHA-256 pin and Apache-2.0 attribution.hinglish_romanas a Latin-script output contract and map it to Whisper'shidecoder token while preserving the contract in health/session responses.auto, so Devanagari leakage cannot silently reach the cursor.Verification
just test— lint, WPS, mypy, package/audit, 508 tests, and Compose config passeduv run scripts/verify-model-pins.py --only whisper.cpp:ggml-apex-hinglish-q5_0.bin— 1 pin checked, 0 mismatcheduv run scripts/generate_model_docs.py --checkPrivacy and security