Skip to content

Promote to production: voice-to-text model cache + audio pause - #77

Merged
slaveofcode merged 2 commits into
mainfrom
develop
Aug 1, 2026
Merged

Promote to production: voice-to-text model cache + audio pause#77
slaveofcode merged 2 commits into
mainfrom
develop

Conversation

@slaveofcode

Copy link
Copy Markdown
Owner

Caches the Whisper transcriber (no re-init per click) and pauses the preview during transcribe.

🤖 Generated with Claude Code

Kresna and others added 2 commits August 1, 2026 13:40
Two issues from testing:
- Every Transcribe click re-initialized the Whisper pipeline (re-reading weights,
  re-running the load progress, blocking the thread). Cache the built transcriber
  by model id and reuse it; the download progress now only shows on first load.
- The audio preview kept playing when pressing stop because ONNX inference blocks
  the main thread and freezes the native controls. Pause the preview
  programmatically when transcribe (or a new recording) starts.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
fix(voice-to-text): cache model + pause preview during transcribe
@slaveofcode
slaveofcode merged commit 1aa20d7 into main Aug 1, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant