Kade Heyborne
73a15d03cd
- Fix state detection priority: dictation now takes precedence over conversation - Fix critical bug: event loop was created but never started, preventing async coroutines from executing - Optimize audio processing: reorder AcceptWaveform/PartialResult checks - Switch to faster Vosk model: vosk-model-en-us-0.22-lgraph for 2-3x speed improvement - Reduce block size from 8000 to 4000 for lower latency - Add filtering to remove spurious 'the', 'a', 'an' words from start/end of transcriptions - Update toggle-dictation.sh to properly clean up conversation lock file - Improve batch audio processing for better responsiveness
20 lines
388 B
TOML
20 lines
388 B
TOML
[project]
|
|
name = "dictation-service"
|
|
version = "0.1.0"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"pynput>=1.8.1",
|
|
"sounddevice>=0.5.3",
|
|
"vosk>=0.3.45",
|
|
"aiohttp>=3.8.0",
|
|
"openai>=1.0.0",
|
|
"pyttsx3>=2.90",
|
|
"requests>=2.28.0",
|
|
"numpy>=2.3.5",
|
|
]
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|