Only the TTS model (~2.4 GB) is required on first run; ASR models are
per-platform curated picks (curated_on in models.yaml) installed on demand.
Every transcription surface returns a typed asr_model_missing error with a
one-click download CTA instead of silently pulling multi-GB Whisper weights.
Settings -> Models is a grouped, platform-aware catalog. New guided
permissions UX (wizard System Check + Settings -> Permissions + mic
pre-flight) with native mic-state checks and OS settings deep-links. New
parakeet-mlx engine brings Parakeet TDT v3 to Apple Silicon (language-gated
capture preference so multilingual dictation never regresses). Docs:
expressive-speech page, Flush/Unload + CPU-fallback triage, clone-length FAQ.
Hardening: preflight fails open for custom model pins, ROCm curation no
longer inherits NVIDIA picks, Windows mic probe reads the NonPackaged
consent key, CaptureWidget setup race fixed, offline-cache CI simulation
fixes so empty-cache runners stay green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
P0 — Refinement blocked every dictation final with no timeout. With refinement
auto:true and a slow/dead LLM endpoint, maybe_refine ran unbounded and blocked
the final send in all three capture_ws handlers (~51s measured; the pill hung
"Transcribing…" until the widget's 15s fallback fired). Fix the class: a hard,
env-tunable budget (OMNIVOICE_REFINE_TIMEOUT_S, default 4s) via a new
maybe_refine_async — a slow/dead endpoint now falls back to the unrefined (but
polished) text within the budget and can NEVER delay the final beyond it. The
LLM HTTP call is bounded to the same budget so the orphaned worker unwinds
instead of holding a connection for the client's full 45s. Refinement is now
also fully best-effort in the legacy handler (it can't turn a good final into
an error frame).
P1 — REST /transcribe lacked polish parity. capture.py never applied
polish_text, so REST returned raw "…test" while the WS returned "…test."
Apply text_polish.polish_text to `text` and `refined_text` (segments stay raw),
so the widget POST fallback and MCP/CLI callers match the live socket.
P1 — The #888 "instant first dictation" preload was a no-op. The preload called
warmup() only `if hasattr`, but SherpaDictationBackend had none, and the WS
handlers built a FRESH backend per session so a warm singleton wasn't reused.
Add SherpaDictationBackend.warmup() (builds the recognizer) and share one warm
recognizer per model id across sessions (get_sherpa_dictation_backend, same
invalidation + a shared lock as the capture singleton); each session keeps its
own decode stream. First dictation no longer pays the 1.3–2.5s load.
P1 — llm_ready is a lie (feeds the P0). It only means "an endpoint is
configured", so a placeholder key reads as ready. The P0 timeout makes a dead
endpoint harmless; add last_refine_status so RefinementPanel flags a
configured-but-failing LLM and links to LLM Providers → Test.
Regression tests (fail-before/pass-after): slow-LLM WS final arrives < budget;
maybe_refine_async hard timeout + status; REST polish parity + refined_text
polish; warmup builds the recognizer and a second session reuses it; the panel
honesty note. Backend refinement/capture_ws/capture/sherpa suites, CJK + route
inventory gates, full vitest (733), lint (0 errors) and format all green.
Co-authored-by: mergetest <test@local>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The live-dictation socket (capture_ws) already runs the final transcript
through the configured local LLM (disfluency/self-correction/punctuation
cleanup, Wave 2.1). The REST /transcribe endpoint — the MCP / CLI / file-upload
surface — only did the always-on hallucination-loop collapse, so agentic and
batch callers couldn't get the same cleaned output.
Add an opt-in `refine` form flag that runs the identical `maybe_refine`
pipeline off-thread:
- OFF by default → existing MCP/CLI callers keep raw-only output and pay no
LLM latency (backward-compatible).
- Honours the user's Settings → Dictation-refinement config and silently
passes through when no LLM backend is configured (cross-platform default
parity — identical no-op everywhere with no LLM).
- Raw `text` is always returned; `refined_text` is added only when the LLM
actually changed the text — same contract the socket emits.
tests/test_capture_refine.py: 13 cases — flag-off no-call, refined_text on
change, no-op/identical omission, and flag parsing. maybe_refine is patched at
its source module since the handler imports it lazily.
