"""Voice worker: the streaming Silero VAD (real ONNX model bundled with faster-whisper, CPU only).""" from __future__ import annotations import wave from pathlib import Path import numpy as np import pytest pytest.importorskip("onnxruntime") pytest.importorskip("faster_whisper") from voice_worker.segmenter import WINDOW # noqa: E402 from voice_worker.vad import SileroVad # noqa: E402 SAMPLE = Path(__file__).resolve().parent.parent / "scripts" / "m0" / "assets" / "ko_samples" / "ko_01.wav" def _speech() -> np.ndarray: with wave.open(str(SAMPLE), "rb") as w: return np.frombuffer(w.readframes(w.getnframes()), dtype="= 0.5).mean() > 0.4 assert silence.max() < 0.2 @pytest.mark.unit def test_each_speaker_stream_keeps_its_own_state(vad): audio = _speech() alone = _probs(vad.stream(), audio) a, b = vad.stream(), vad.stream() n = len(audio) // WINDOW * WINDOW interleaved = [] for i in range(0, n, WINDOW): interleaved.append(a.prob(audio[i:i + WINDOW])) b.prob(np.zeros(WINDOW, dtype=np.float32)) # another speaker in silence between every window assert np.allclose(alone, interleaved, atol=1e-5)