fmartingr/tellme
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Implement Phase 2: Real offline speech-to-text with whisper.cpp

Browse source 
- Add SwiftWhisper integration for real whisper.cpp support with Metal acceleration
- Implement complete WhisperCPPEngine with audio transcription and text normalization
- Build ModelManager with curated catalog, downloads, and Core ML encoder support
- Create preferences window with model management UI (download, select, delete)
- Add NSStatusItem menu bar with model status display
- Integrate STT pipeline: hotkey → audio capture → whisper transcription
- Add model setup alerts when no model is loaded
- Support offline operation with performance targets met (<4s for 10s audio)
- Store models in ~/Library/Application Support/MenuWhisper/Models/

Phase 2 TECHSPEC requirements fully implemented and tested.
This commit is contained in:
Felipe M 2025-09-19 08:31:35 +02:00
parent 6e768a7753
commit 5663f3c3de
Signed by: fmartingr
GPG key ID: CCFBC5637D4000A8
12 changed files with 1500 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

77
Sources/App/Resources/Localizations/en.lproj/Localizable.strings Normal file
View file

@ -0,0 +1,77 @@
/* Menu-Whisper - English Localization */
/* General */
"app.name" = "Menu-Whisper";
"general.ok" = "OK";
"general.cancel" = "Cancel";
"general.continue" = "Continue";
"general.settings" = "Settings";
"general.quit" = "Quit";
/* Menu Bar */
"menubar.idle" = "Idle";
"menubar.listening" = "Listening";
"menubar.processing" = "Processing";
"menubar.preferences" = "Preferences...";
"menubar.quit" = "Quit Menu-Whisper";
/* HUD States */
"hud.listening" = "Listening...";
"hud.processing" = "Transcribing...";
"hud.cancel" = "Press Esc to cancel";
/* Permissions */
"permissions.microphone.title" = "Microphone Access Required";
"permissions.microphone.message" = "Menu-Whisper needs access to your microphone to perform speech-to-text transcription.";
"permissions.accessibility.title" = "Accessibility Access Required";
"permissions.accessibility.message" = "Menu-Whisper needs Accessibility access to insert transcribed text into applications.";
"permissions.input_monitoring.title" = "Input Monitoring Required";
"permissions.input_monitoring.message" = "Menu-Whisper needs Input Monitoring access to register global hotkeys.";
"permissions.open_settings" = "Open System Settings";
/* Preferences Window */
"preferences.title" = "Menu-Whisper Preferences";
"preferences.general" = "General";
"preferences.models" = "Models";
"preferences.hotkeys" = "Hotkeys";
"preferences.insertion" = "Text Insertion";
"preferences.advanced" = "Advanced";
/* General Preferences */
"preferences.general.hotkey" = "Global Hotkey:";
"preferences.general.mode" = "Activation Mode:";
"preferences.general.mode.push_to_talk" = "Push-to-talk";
"preferences.general.mode.toggle" = "Toggle";
"preferences.general.sounds" = "Play sounds for start/stop";
"preferences.general.limit" = "Dictation time limit (minutes):";
/* Model Preferences */
"preferences.models.title" = "Speech Recognition Models";
"preferences.models.active" = "Active Model:";
"preferences.models.language" = "Language:";
"preferences.models.language.auto" = "Auto-detect";
"preferences.models.download" = "Download";
"preferences.models.delete" = "Delete";
"preferences.models.size" = "Size:";
"preferences.models.languages" = "Languages:";
/* Insertion Preferences */
"preferences.insertion.method" = "Insertion Method:";
"preferences.insertion.method.paste" = "Paste (⌘V)";
"preferences.insertion.method.type" = "Type characters";
"preferences.insertion.preview" = "Show preview before inserting";
"preferences.insertion.secure_input" = "Secure Input Detected";
"preferences.insertion.secure_input.message" = "Text insertion is disabled in secure contexts. Text has been copied to clipboard.";
/* Errors */
"error.audio.failed" = "Failed to access microphone";
"error.model.not_found" = "Speech recognition model not found";
"error.model.load_failed" = "Failed to load speech recognition model";
"error.transcription.failed" = "Speech transcription failed";
"error.download.failed" = "Model download failed";
"error.download.verification_failed" = "Model verification failed";
/* Success Messages */
"success.model.downloaded" = "Model downloaded successfully";
"success.settings.exported" = "Settings exported successfully";
"success.settings.imported" = "Settings imported successfully";