Detect the language once for auto-detect file passes on the chunked path (D-053)

Transformers.js has no Whisper language detection and silently decoded
Danish as English whenever "Skip silence" was off or unavailable.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Lucas WintherandClaude Opus 5.5 committed 2026-10-30 14:35:09 +01:00
1 parent 3583d60847
commit dd9dfc628b
6 files changed
+112 -6

No files matched your search

+3
View File
@@ -163,6 +163,9 @@ environment). See `WorkBreakdown.md` for the itemized checklist.)
(`VocabularyHint`, stored in localStorage by `lib/hint.ts`), raw as typed (D-048).
5. Worker runs the pipeline (chunked, with timestamps), streaming partial results
back via `{type:"partial"}` messages; final result as `{type:"result"}`.
With auto-detect on a multilingual model, it first detects the language on
the first 30 s (`worker/language.ts`, D-053) and pins it — Transformers.js
itself would default to English.
A hint becomes `<|startofprev|> hint.` once per pass (`worker/prompt.ts`,
cut to a 120-token prompt budget at a whole word) and is prepended
to the decoder input of every 30 s window by a wrapper around the model's