dba78a2766
- Detection: broaden request-starters, handle contractions, allow 1-word '?' - Audio: PTT pre-roll (no clipped first word), drop Whisper silence hallucinations, greedy decoding + domain initial_prompt for faster/cleaner transcription - AI: cap spoken-answer tokens so replies return at conversational speed - Overlay: answers persist (no auto-hide); wire Ctrl+Shift+H show/hide toggle - Screen capture: freeze-frame at hotkey press (immune to focus-blur lockouts), hide selector from screen-share (NSWindowSharingNone), higher capture resolution - Stop tracking models/ and *.zip (large binaries; add to .gitignore) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
36 lines
454 B
Plaintext
36 lines
454 B
Plaintext
# Core dependencies
|
|
torch
|
|
torchvision
|
|
|
|
# Audio processing
|
|
sounddevice
|
|
SpeechRecognition
|
|
webrtcvad
|
|
pyaudio; platform_system == "Windows"
|
|
|
|
# Screen capture & OCR
|
|
mss
|
|
Pillow
|
|
pytesseract
|
|
easyocr
|
|
opencv-python
|
|
|
|
# Local LLM
|
|
ctransformers
|
|
llama-cpp-python
|
|
|
|
# GUI
|
|
PyQt5
|
|
pyobjc-framework-Cocoa; platform_system == "Darwin"
|
|
pywin32; platform_system == "Windows"
|
|
|
|
# Utilities
|
|
pyautogui
|
|
keyboard
|
|
pynput
|
|
pyyaml
|
|
numpy
|
|
scipy
|
|
faster-whisper
|
|
pyaudio
|
|
sentence-transformers |