feat: add webrtcvad-based smart command-end detection
Replace the fixed 10s post-wake-word listen window with a VAD-driven loop. Once at least 500ms of speech have been seen, 1.2s of silence closes the window. Hard cap at 15s as a safety net. Tunable in config.py via VAD_AGGRESSIVENESS, COMMAND_END_SILENCE_MS, COMMAND_MIN_SPEECH_MS, COMMAND_MIN_LISTEN_MS, COMMAND_MAX_LISTEN_MS.
This commit is contained in:
parent
277921ce14
commit
794d923bf9
3 changed files with 45 additions and 6 deletions
|
|
@ -4,6 +4,9 @@ pvrecorder
|
|||
# Vosk
|
||||
vosk
|
||||
|
||||
# Voice activity detection (smart command-end)
|
||||
webrtcvad-wheels
|
||||
|
||||
# Groq / OpenAI-compatible LLM
|
||||
openai>=1.0
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue