Clarify that the spoken-language setting only affects cloud STT#283
Open
castawait wants to merge 1 commit into
Open
Clarify that the spoken-language setting only affects cloud STT#283castawait wants to merge 1 commit into
castawait wants to merge 1 commit into
Conversation
The spoken-language selection is only ever forwarded to the cloud providers (WisprFlow, Kirinki). The on-device Cactus model ignores it: HybridTranscriptionService.route() passes language only to the remote path, while transcribeLocal/transcribeLocalForFallback take no language and the native cactusTranscribe is always called with null prompt and options. So choosing a language is a no-op on local transcription. Make that clear in the UI: * Rename the Watch Settings item and picker dialog to "Cloud Spoken Language" and move it directly under "Cloud Recognition Provider" so it reads as part of the cloud section. * Fold the current selection into the subtitle and add a note that the on-device model detects language automatically. * Reword the picker dialog note to say on-device transcription ignores this setting. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
|
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The spoken-language setting currently reads as though it might also affect on-device transcription. In practice the selection is only sent to the cloud providers (WisprFlow and Kirinki); the local Cactus model does not use it. This PR updates the UI to reflect that. There is no behavior change.
Changes:
For reference, the routing:
HybridTranscriptionService.route()forwardslanguageonly to the remote path.transcribeLocalandtranscribeLocalForFallbacktake no language, and the nativecactusTranscribecall passes null for prompt and options. The Rebble local fallback inSTTRouteris the same.One file, copy and layout only:
pebble/.../ui/WatchSettingsScreen.kt.Claude helped put this PR together.