aharrison-fullerandClaude Opus 5
4286e88344
Loads parakeet-mlx in-process (no HTTP hop) and serves it over the Wyoming
protocol. On an M4 Mac mini this transcribes typical voice commands in ~110ms
versus ~1150ms for a whisper.cpp large-v3 setup, with identical accuracy on a
ten-command benchmark.
Two behaviours matter beyond speed: silence returns an empty string rather
than whisper's "Thank you." hallucination, and there is no decoder context
carried between requests.
Notable implementation details, all covered by mutation-checked regression
tests:
- MLX streams are thread-local, so the model is loaded and evaluated on a
single dedicated worker thread. Splitting those raises
"There is no Stream(cpu, 1) in current thread".
- parakeet_mlx.load_audio() shells out to ffmpeg, which is unnecessary here
since Wyoming delivers 16kHz mono PCM. The mel is built directly via
get_logmel(), whose input must be float32 -- it views the complex STFT
output as the input dtype, so anything narrower doubles the mel bin count.
- Wyoming's run loop has no except clause, so an exception escaping
handle_event closes the connection without sending a Transcript and Home
Assistant waits indefinitely. Failures are caught and returned as an empty
transcript instead.
Defaults to parakeet-tdt-0.6b-v2 rather than the newer multilingual v3
because v2 emits digits ("21 degrees") where v3 spells numbers out, and
Home Assistant's local intent matching expects digits.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
13 lines
267 B
Python
13 lines
267 B
Python
import numpy as np
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def pcm():
|
|
"""Build int16 mono PCM bytes of a given sample count."""
|
|
|
|
def _pcm(n_samples: int, value: int = 8192) -> bytes:
|
|
return np.full(n_samples, value, dtype=np.int16).tobytes()
|
|
|
|
return _pcm
|