75 lines
2.5 KiB
Python
75 lines
2.5 KiB
Python
|
# SPDX-License-Identifier: Apache-2.0
|
||
|
|
"""Dump the Python metrics as the reference for the browser port (web/dsp.js).
|
||
|
|
|
||
|
|
Each audio file is loaded exactly as the desktop app loads it
|
||
|
|
(`master_core.AudioFile`); the mono signal the metrics see is written out next
|
||
|
|
to every metric's `compute()` result. `parity.mjs` feeds that same signal to
|
||
|
|
dsp.js, so the comparison isolates the DSP port from decoder differences.
|
||
|
|
|
||
|
|
uv run --no-project --with librosa --with pyloudnorm --with scipy --with mutagen \
|
||
|
|
python tests/parity/reference.py OUT_DIR AUDIO...
|
||
|
|
|
||
|
|
Writes OUT_DIR/<file name>/{mono.f32, reference.json, spectrogram.f32}.
|
||
|
|
"""
|
||
|
|
|
||
|
|
import json
|
||
|
|
import sys
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
|
||
|
|
|
||
|
|
from master_core import AudioFile # noqa: E402
|
||
|
|
from metrics import METRICS # noqa: E402
|
||
|
|
|
||
|
|
|
||
|
|
def _jsonable(value):
|
||
|
|
if isinstance(value, np.ndarray):
|
||
|
|
return [float(v) if np.isfinite(v) else None for v in value.astype(np.float64).ravel()]
|
||
|
|
if isinstance(value, (float, np.floating)):
|
||
|
|
return float(value) if np.isfinite(value) else None
|
||
|
|
return value
|
||
|
|
|
||
|
|
|
||
|
|
def main() -> None:
|
||
|
|
out = Path(sys.argv[1])
|
||
|
|
out.mkdir(parents=True, exist_ok=True)
|
||
|
|
for path in sys.argv[2:]:
|
||
|
|
name = Path(path).name
|
||
|
|
try:
|
||
|
|
audio = AudioFile(path)
|
||
|
|
except Exception as exc: # librosa can't read every container the browser can
|
||
|
|
print(f"{name}: skipped ({exc})")
|
||
|
|
continue
|
||
|
|
|
||
|
|
target = out / name
|
||
|
|
target.mkdir(exist_ok=True)
|
||
|
|
audio.y_mono.astype(np.float32).tofile(target / "mono.f32")
|
||
|
|
|
||
|
|
results = {}
|
||
|
|
for metric_id, metric in METRICS.items():
|
||
|
|
data = metric.compute(audio)
|
||
|
|
if metric_id == "spectrogram":
|
||
|
|
s_db = np.ascontiguousarray(data["s_db"], dtype=np.float32)
|
||
|
|
s_db.tofile(target / "spectrogram.f32")
|
||
|
|
results[metric_id] = {
|
||
|
|
"rows": int(s_db.shape[0]), "cols": int(s_db.shape[1]),
|
||
|
|
"times": _jsonable(data["times"]), "freqs": _jsonable(data["freqs"]),
|
||
|
|
"nyquist": float(data["nyquist"]),
|
||
|
|
}
|
||
|
|
else:
|
||
|
|
results[metric_id] = {key: _jsonable(val) for key, val in data.items()}
|
||
|
|
|
||
|
|
meta = {
|
||
|
|
"file": name, "sr": int(audio.sr), "n": int(len(audio.y_mono)),
|
||
|
|
"song_name": audio.song_name,
|
||
|
|
"max_amplitude": float(audio.max_amplitude), "avg_amplitude": float(audio.avg_amplitude),
|
||
|
|
}
|
||
|
|
(target / "reference.json").write_text(json.dumps({"meta": meta, "metrics": results}))
|
||
|
|
print(f"{name}: {audio.sr} Hz, {len(audio.y_mono) / audio.sr:.2f} s, song_name={audio.song_name!r}")
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|