drum-sample-extractor / docs /benchmark-subprocesses.json
ChatGPT
feat: add full-context reproduction and clearer controls
0b5f0f0
Raw
History Blame Contribute Delete
7.84 kB
{
"clustering_mode": "batch_quality",
"runs": [
{
"pattern": "rock",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "batch_quality",
"audio_duration_sec": 4.75,
"total_duration_sec": 2.994395,
"realtime_factor": 0.630399,
"hit_count": 12,
"cluster_count": 7,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.02592192699921725,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.1751658609991864,
"status": "done",
"detail": "120.2 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 2.1905335589999595,
"status": "done",
"detail": "12 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.09557517999928677,
"status": "done",
"detail": "bright:5, hihat_open:6, kick:1"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.014000580998981604,
"status": "done",
"detail": "7 clusters \u00b7 batch quality"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.08321280500058492,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0006027010003890609,
"status": "done",
"detail": "2 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.40873212500082445,
"status": "done",
"detail": "7 samples + 12 review hits + MIDI + full-context reproduction + ZIP"
}
]
},
{
"pattern": "funk",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "batch_quality",
"audio_duration_sec": 4.874989,
"total_duration_sec": 2.802354,
"realtime_factor": 0.574843,
"hit_count": 23,
"cluster_count": 2,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.02253025699974387,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.09380031600085204,
"status": "done",
"detail": "161.5 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 2.1897132599988254,
"status": "done",
"detail": "23 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.017409414000212564,
"status": "done",
"detail": "bright:13, hihat_closed:4, hihat_open:4, kick:1, mid:1"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.03413462400021672,
"status": "done",
"detail": "2 clusters \u00b7 batch quality"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.26413379800033,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0011682919994200347,
"status": "done",
"detail": "2 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.17886992200146778,
"status": "done",
"detail": "2 samples + 23 review hits + MIDI + full-context reproduction + ZIP"
}
]
},
{
"pattern": "halftime",
"bars": 2,
"bpm": 120.0,
"run_index": 0,
"clustering_mode": "batch_quality",
"audio_duration_sec": 4.874989,
"total_duration_sec": 2.514399,
"realtime_factor": 0.515775,
"hit_count": 31,
"cluster_count": 3,
"stages": [
{
"key": "stem",
"label": "Stem extraction / source load",
"duration_sec": 0.0255989449997287,
"status": "done",
"detail": "loaded full mix \u00b7 cached \u00b7 reproduction uses full mix"
},
{
"key": "bpm",
"label": "Tempo detection",
"duration_sec": 0.08472461699966516,
"status": "done",
"detail": "120.2 BPM"
},
{
"key": "onsets",
"label": "Onset detection + slicing",
"duration_sec": 1.905502139001328,
"status": "done",
"detail": "31 hits"
},
{
"key": "classification",
"label": "Spectral rule classification",
"duration_sec": 0.018339307000132976,
"status": "done",
"detail": "bright:4, hihat_closed:25, hihat_open:2"
},
{
"key": "clustering",
"label": "Mel fingerprint + transient NCC clustering",
"duration_sec": 0.05202830600137531,
"status": "done",
"detail": "3 clusters \u00b7 batch quality"
},
{
"key": "selection",
"label": "Best representative scoring",
"duration_sec": 0.24863046999962535,
"status": "done",
"detail": "quality-scored representatives"
},
{
"key": "synthesis",
"label": "Optional sample synthesis",
"duration_sec": 0.0012351730001682881,
"status": "done",
"detail": "3 synthesized alternates"
},
{
"key": "export",
"label": "MIDI, reproduced mix, WAV, ZIP export",
"duration_sec": 0.17784613499861734,
"status": "done",
"detail": "3 samples + 31 review hits + MIDI + full-context reproduction + ZIP"
}
]
}
],
"summary": [
{
"stage": "stem",
"mean_sec": 0.024684,
"median_sec": 0.025599,
"min_sec": 0.02253,
"max_sec": 0.025922
},
{
"stage": "bpm",
"mean_sec": 0.117897,
"median_sec": 0.0938,
"min_sec": 0.084725,
"max_sec": 0.175166
},
{
"stage": "onsets",
"mean_sec": 2.09525,
"median_sec": 2.189713,
"min_sec": 1.905502,
"max_sec": 2.190534
},
{
"stage": "classification",
"mean_sec": 0.043775,
"median_sec": 0.018339,
"min_sec": 0.017409,
"max_sec": 0.095575
},
{
"stage": "clustering",
"mean_sec": 0.033388,
"median_sec": 0.034135,
"min_sec": 0.014001,
"max_sec": 0.052028
},
{
"stage": "selection",
"mean_sec": 0.198659,
"median_sec": 0.24863,
"min_sec": 0.083213,
"max_sec": 0.264134
},
{
"stage": "synthesis",
"mean_sec": 0.001002,
"median_sec": 0.001168,
"min_sec": 0.000603,
"max_sec": 0.001235
},
{
"stage": "export",
"mean_sec": 0.255149,
"median_sec": 0.17887,
"min_sec": 0.177846,
"max_sec": 0.408732
}
]
}