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
22 lines
669 B
Python
22 lines
669 B
Python
import sounddevice as sd
|
|
from vosk import Model, KaldiRecognizer
|
|
from pynput.keyboard import Controller
|
|
import time
|
|
|
|
with open("/home/universal/.gemini/tmp/428d098e581799ff7817b2001dd545f7b891975897338dd78498cc16582e004f/test.log", "w") as f:
|
|
f.write("test")
|
|
|
|
SAMPLE_RATE = 16000
|
|
BLOCK_SIZE = 8000
|
|
MODEL_NAME = "vosk-model-small-en-us-0.15"
|
|
|
|
def audio_callback(indata, frames, time, status):
|
|
pass
|
|
|
|
keyboard = Controller()
|
|
model = Model(MODEL_NAME)
|
|
recognizer = KaldiRecognizer(model, SAMPLE_RATE)
|
|
|
|
with sd.RawInputStream(samplerate=SAMPLE_RATE, blocksize=BLOCK_SIZE, dtype='int16',
|
|
channels=1, callback=audio_callback):
|
|
time.sleep(10) |