Spaces:
Running
Running
File size: 1,710 Bytes
330f477 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | #!/usr/bin/env python3
from __future__ import annotations
import argparse
import asyncio
import json
import resource
import sys
import time
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from openmusic_analysis.application import build_service
async def main() -> None:
parser = argparse.ArgumentParser(description="Measure model load and per-representation latency")
parser.add_argument("audio", type=Path)
parser.add_argument("--lyrics", type=Path)
args = parser.parse_args()
service = build_service()
lyrics = args.lyrics.read_text(encoding="utf-8") if args.lyrics else None
measurements = {}
started = time.perf_counter()
await service.load_models()
measurements["model_startup_seconds"] = time.perf_counter() - started
representations = ["audio.global", "audio.temporal"]
if lyrics is not None:
representations.append("lyrics.global")
for representation in representations:
started = time.perf_counter()
await service.analyze(
args.audio,
lyrics=lyrics,
requested_representations=[representation],
track_id=None,
content_identity=None,
)
measurements[f"{representation}_seconds"] = time.perf_counter() - started
measurements["peak_process_rss_platform_units"] = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
try:
import torch
if torch.cuda.is_available():
measurements["peak_cuda_memory_bytes"] = torch.cuda.max_memory_allocated()
except ImportError:
pass
print(json.dumps(measurements, indent=2))
if __name__ == "__main__":
asyncio.run(main())
|