Ryan wants the repo and TestFlight to stay on 0.2.0 while the App Store gets 0.2.1. ci_post_clone.sh now rewrites MARKETING_VERSION from a tag ios-beta-appstore-<version> before xcodegen; other builds are untouched.
Verified sh -n and the sed against a copy of project.yml (all three targets become 0.2.1).
* ios: clean up what I say with Hex's on-device dictation tagger (experiment)
What changed
- Experiments › Clean up what I say (off by default, App Group key
experiments.cleanupTagger): Hex's trained cleanup tagger removes ums,
repeats, and the words a spoken correction replaces ("3pm, actually 4pm"),
on the iPhone, in in-keyboard dictation and in app dictation. It runs after
transcription and learned fixes (in the app also after custom vocabulary),
before Apple Intelligence cleanup, translation, and formatting, and never
for Verbatim. When both cleanups are on, Apple Intelligence now receives the
tagged text instead of the raw transcript; nothing else changes while the
experiment is off.
- Model: the BERT L-4/H-512 token classifier (ckpt-1200k-l4h512) converted to
an int8 Core ML ML Program (coremltools 9, fp16 compute, enumerated lengths
16/32/64/128 plus a length input that masks the padding; the output is
logit(DELETE) - logit(KEEP)), 28.5 MB, with its WordPiece vocabulary. Both
ship once, in HEXKeyboard.appex (HEXKeyboard/CleanupTagger/), and the app
loads them from its embedded keyboard extension. Core ML codegen is off for
the keyboard target.
- HEXShared: CleanupTokenizer (Hugging Face BertTokenizer: special tokens,
BertNormalizer, BertPreTokenizer, WordPiece, byte-exact vocabulary keys,
HF's Unicode 8.0 character classes), CleanupReconstruction (a port of
js/reconstruct.js with JavaScript's UTF-16 casing), and CleanupTagger
(chunks of whole words within 128 tokens, P(DELETE) > 0.98, one serial
queue, 150 ms budget). A timeout, an error, or a result with no words left
keeps the transcript. The model loads when a dictation starts recording with
the experiment on, stays loaded, and is freed on a memory warning. It runs
on the Neural Engine or the CPU, never the GPU.
- Call sites: one each in KeyboardLocalDictation (after DictationCorrections,
before translation) and DictationController (after VocabularySpelling,
before the Apple Intelligence pass). prepareIfEnabled runs at recording
start, in KeyboardViewController and in DictationController.startRecording.
Why
- In the simulator the first load took 0.15 s on the CPU and 0.8 s on the GPU
path, both over the 150 ms budget. So loading starts when recording starts,
and the GPU isn't used (it also added 30 MB of footprint, against 3 MB on the
CPU, which keeps the int8 weights memory-mapped).
- Threshold 0.98, not the exported 0.95: 1/45 false deletes on hand-written
clean sentences against 3/45, with the same self-correction accuracy.
Verified
- xcodebuild test on the iPhone 18 Pro simulator: 168 tests, 0 failures,
including the new CleanupTaggerTests and DictationControllerTests
testCleanupTaggerRunsAfterLearnedFixesAndSkipsVerbatim. After the fixtures
were rewritten one case per line (same content), CleanupTaggerTests and
DictationControllerTests passed again (28 tests).
- Parity on the 137 hand-written sentences at 0.98: labels match the fp32
checkpoint on all 1,128 words, and 136/137 outputs match the ONNX int8
pipeline. #120 ("The cat keeps trying to scratch that chair.") differs on
two words that ONNX keeps (P 0.9725/0.9794) and Core ML deletes (0.984).
The fp32 checkpoint also deletes them (0.9879/0.9853), so the difference
comes from ONNX's int8 activations. 128/137 outputs match the hand-written
targets. The tokenizer matches HF on 1,891 words, and reconstruction matches
reconstruct.js on 670 cases.
- Simulator, CPU path: load 140-161 ms, first sentence after load about 8 ms,
then 3.3 ms median and 7.5 ms p95 per sentence; phys_footprint +2.9 MB.
- The Release generic iOS build with CODE_SIGNING_ALLOWED=NO succeeds.
HEXKeyboard.appex is 30.2 MB (model 27.8 MB, vocabulary 0.2 MB).
- Not verified on a physical iPhone: Neural Engine load time, latency, and the
keyboard extension's footprint next to Apple Speech.
Note: this adds a 28.4 MB binary (weight.bin) to git; the repo has no LFS.
* Fetch the cleanup tagger's Core ML model at build time instead of committing it
The 27 MB mlpackage would have been ~30x the largest file in the repo, kept in history forever. It is now the ios-model-cleanup-tagger-1 release asset; ios/scripts/fetch-cleanup-model.sh downloads it, checks its SHA-256, and skips when the pinned copy is already in place. Xcode Cloud runs it in ci_post_clone.sh before xcodegen; the folder is gitignored.
Verified the fetched package is byte-identical to the one the tests ran against (diff -r), and a second run is a no-op.
* iOS: move Hex for iPhone to Anomaly's Apple team
(cherry picked from commit 09061502ff)
* Cut Hex Mobile TestFlight betas with a dedicated release tag
Connect the Anomaly app record and pin the mobile package graph. Cut ios-beta prereleases from dev at the scheduled windows or on dispatch, skipping unchanged mobile inputs instead of creating desktop releases or allocating build numbers locally. Prepare the generated project for the Cloud archive after clone.
Verified actionlint, duplicate and desktop-only skips, strict SwiftPM resolution, and an unsigned Release device archive containing the app, keyboard, and widgets. First Xcode Cloud onboarding and signed distribution are still pending.
---------
Co-authored-by: Kit Langton <kit.langton@gmail.com>