Files
CyberGril/samples/companion/tools/check_driver_audio.py
T

93 lines
3.8 KiB
Python

"""Run with the pinned driver venv: python check_driver_audio.py PRIVATE_DRIVER."""
import hashlib
import importlib.util
import pathlib
import sys
import time
import unittest
from types import SimpleNamespace
import numpy as np
ROOT = pathlib.Path(sys.argv.pop(1)).resolve()
sys.path.insert(0, str(ROOT))
spec = importlib.util.spec_from_file_location('driver_webrtc', ROOT / 'server/webrtc.py')
driver = importlib.util.module_from_spec(spec)
spec.loader.exec_module(driver)
PendingAudio = driver.PendingAudio
class QueueChecks(unittest.TestCase):
def test_idle_is_bounded_speech_and_events_are_lossless(self):
pending = PendingAudio()
expected = []
for i in range(2000):
if i % 100 == 0:
# Real zero PCM and custom audio are not synthetic silence.
item = (i, {'event': i} if i % 200 else {}, 0 if i % 200 else 2)
expected.append(item)
else:
item = (i, None, 1)
pending.put(item)
actual = list(pending.queue)
self.assertEqual([x for x in actual if x[2] != 1], expected)
self.assertEqual(sum(x[2] == 1 for x in actual), 3)
self.assertLessEqual(pending.high_water, len(expected) + 3)
self.assertGreater(pending.dropped_silence, 1900)
marker = ('event', {'end': True}, 1)
pending.put(marker)
for i in range(50):
pending.put((i, None, 1))
self.assertIn(marker, list(pending.queue))
def test_real_audio_has_bounded_backpressure(self):
pending = PendingAudio()
for i in range(100):
pending.put((i, None, 0))
import queue
with self.assertRaises(queue.Full):
pending.put((101, None, 0), block=False)
self.assertEqual([x[0] for x in pending.queue], list(range(100)))
def test_warmup_drains_all_context(self):
from avatars.audio_features.base_asr import BaseASR
asr = BaseASR(SimpleNamespace(fps=25, batch_size=8, l=10, r=10))
asr.warm_up()
self.assertEqual(len(asr.frames), 20)
self.assertTrue(asr.output_queue.empty())
first = np.arange(320, dtype=np.float32)
asr.put_audio_frame(first, {'first': True})
frame = asr.get_audio_frame()
np.testing.assert_array_equal(frame.data, first)
self.assertEqual(frame.type, 0)
self.assertEqual(frame.userdata, {'first': True})
class ClockChecks(unittest.IsolatedAsyncioTestCase):
async def test_starvation_preserves_cadence_and_first_pcm(self):
player = SimpleNamespace(_start=lambda _: None, _stop=lambda _: None, notify=lambda _: None)
track = driver.PlayerStreamTrack(player, 'audio')
frame = driver.AudioFrame.from_ndarray(np.ones((1, 320), np.int16), format='s16', layout='mono')
frame.sample_rate = 16000
track._queue.put((frame, None, 0))
start = time.monotonic()
frames = [await track.recv() for _ in range(15)]
self.assertEqual([f.pts for f in frames], list(range(0, 15 * 320, 320)))
self.assertGreater(time.monotonic() - start, 0.25)
self.assertLess(time.monotonic() - start, 0.5)
self.assertTrue(all(not f.to_ndarray().any() for f in frames[1:]))
# Resume with exact first speech PCM, without trimming any syllable.
pcm = np.arange(320, dtype=np.int16).reshape(1, -1)
voice = driver.AudioFrame.from_ndarray(pcm, format='s16', layout='mono')
voice.sample_rate = 16000
track._queue.put((voice, {'start': True}, 0))
out = await track.recv()
self.assertEqual(out.pts, 15 * 320)
self.assertEqual(hashlib.sha256(out.to_ndarray().tobytes()).digest(), hashlib.sha256(pcm.tobytes()).digest())
track.stop()
if __name__ == '__main__':
unittest.main(verbosity=2)