drum-sample-extractor / docs /benchmark-online-preview.json
ChatGPT
feat: add full-context reproduction and clearer controls
0b5f0f0
Raw
History Blame Contribute Delete
7.88 kB
{
"clustering_mode": "online_preview",
"runs": [
{
"pattern": "rock",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "online_preview",
"audio_duration_sec": 4.75,
"total_duration_sec": 2.619948,
"realtime_factor": 0.551568,
"hit_count": 14,
"cluster_count": 11,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.025709866000397597,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.17244149500038475,
"status": "done",
"detail": "120.2 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 2.01123834900136,
"status": "done",
"detail": "14 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.015600401000483544,
"status": "done",
"detail": "bright:4, hihat_closed:1, hihat_open:7, kick:1, mid:1"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.08166359800088685,
"status": "done",
"detail": "11 clusters \u00b7 online preview"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.02976710500115587,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0003646059994935058,
"status": "done",
"detail": "2 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.28268050299993774,
"status": "done",
"detail": "11 samples + 14 review hits + MIDI + full-context reproduction + ZIP"
}
]
},
{
"pattern": "funk",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "online_preview",
"audio_duration_sec": 4.874989,
"total_duration_sec": 3.096466,
"realtime_factor": 0.635174,
"hit_count": 29,
"cluster_count": 12,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.02813513600085571,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.0898798819998774,
"status": "done",
"detail": "161.5 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 2.39328171499983,
"status": "done",
"detail": "29 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.01869549100047152,
"status": "done",
"detail": "bright:12, cymbal:1, hihat_closed:9, hihat_open:3, mid:4"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.03839712700028031,
"status": "done",
"detail": "12 clusters \u00b7 online preview"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.2286190050017467,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0011234290013817372,
"status": "done",
"detail": "5 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.29779865499949665,
"status": "done",
"detail": "12 samples + 29 review hits + MIDI + full-context reproduction + ZIP"
}
]
},
{
"pattern": "halftime",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "online_preview",
"audio_duration_sec": 4.874989,
"total_duration_sec": 2.58942,
"realtime_factor": 0.531164,
"hit_count": 29,
"cluster_count": 12,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.0707627699994191,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.1129706889987574,
"status": "done",
"detail": "120.2 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 1.902288953999232,
"status": "done",
"detail": "29 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.018896421999670565,
"status": "done",
"detail": "bright:4, hihat_closed:23, hihat_open:2"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.10450396400119644,
"status": "done",
"detail": "12 clusters \u00b7 online preview"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.11157589499998721,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0010697859997890191,
"status": "done",
"detail": "6 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.2668189519990847,
"status": "done",
"detail": "12 samples + 29 review hits + MIDI + full-context reproduction + ZIP"
}
]
}
],
"summary": [
{
"stage": "stem",
"mean_sec": 0.041536,
"median_sec": 0.028135,
"min_sec": 0.02571,
"max_sec": 0.070763
},
{
"stage": "bpm",
"mean_sec": 0.125097,
"median_sec": 0.112971,
"min_sec": 0.08988,
"max_sec": 0.172441
},
{
"stage": "onsets",
"mean_sec": 2.10227,
"median_sec": 2.011238,
"min_sec": 1.902289,
"max_sec": 2.393282
},
{
"stage": "classification",
"mean_sec": 0.017731,
"median_sec": 0.018695,
"min_sec": 0.0156,
"max_sec": 0.018896
},
{
"stage": "clustering",
"mean_sec": 0.074855,
"median_sec": 0.081664,
"min_sec": 0.038397,
"max_sec": 0.104504
},
{
"stage": "selection",
"mean_sec": 0.123321,
"median_sec": 0.111576,
"min_sec": 0.029767,
"max_sec": 0.228619
},
{
"stage": "synthesis",
"mean_sec": 0.000853,
"median_sec": 0.00107,
"min_sec": 0.000365,
"max_sec": 0.001123
},
{
"stage": "export",
"mean_sec": 0.282433,
"median_sec": 0.282681,
"min_sec": 0.266819,
"max_sec": 0.297799
}
]
}