42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
|
import math
|
||
|
|
import struct
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
from hass.vad import VadConfig, VadSegmenter
|
||
|
|
|
||
|
|
|
||
|
|
def _sine_frame(sample_rate: int, freq_hz: float, frame_ms: int = 20) -> bytes:
|
||
|
|
samples = int(sample_rate * frame_ms / 1000)
|
||
|
|
values = [
|
||
|
|
int(10000 * math.sin(2 * math.pi * freq_hz * i / sample_rate))
|
||
|
|
for i in range(samples)
|
||
|
|
]
|
||
|
|
return struct.pack("<" + "h" * samples, *values)
|
||
|
|
|
||
|
|
|
||
|
|
def _silence_frame(sample_rate: int, frame_ms: int = 20) -> bytes:
|
||
|
|
samples = int(sample_rate * frame_ms / 1000)
|
||
|
|
return b"\x00\x00" * samples
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize("min_silence_ms", [40, 60])
|
||
|
|
def test_vad_emits_utterance(min_silence_ms: int):
|
||
|
|
config = VadConfig(
|
||
|
|
aggressiveness=1,
|
||
|
|
min_silence_ms=min_silence_ms,
|
||
|
|
max_utterance_ms=2000,
|
||
|
|
sample_rate=16000,
|
||
|
|
)
|
||
|
|
seg = VadSegmenter(config)
|
||
|
|
|
||
|
|
utterances = []
|
||
|
|
for _ in range(6):
|
||
|
|
utterances.extend(seg.feed(_sine_frame(16000, 440.0)))
|
||
|
|
for _ in range(6):
|
||
|
|
utterances.extend(seg.feed(_silence_frame(16000)))
|
||
|
|
|
||
|
|
assert len(utterances) >= 1
|
||
|
|
assert len(utterances[0]) > 0
|
||
|
|
|