h3-blackwell-runtime/benchmarks/audio-dialogue-format-sweep-sage2-seeds440420-440429.json

51 lines
1.7 KiB
JSON
Raw Normal View History

{
"name": "audio-dialogue-format-sweep-sage2-seeds440420-440429",
"measured_at": "2026-08-21",
"hardware": "NVIDIA GB10",
"model": "minimax_h3_fl2va_pruned_nvfp4.safetensors",
"attention": "sage2",
"scheduler": "beta",
"sampler": "res_multistep",
"steps": 12,
"resolution": [864, 480],
"frames": 141,
"seeds": [440420, 440421, 440422, 440423, 440424, 440425, 440426, 440427, 440428, 440429],
"comparison": "Identical dialogue semantics with <d>[English]...</d> markup versus quoted speech",
"cases": 20,
"aggregate": {
"quoted_first_100ms_peak_reduction_db": {
"mean": 20.112007323193758,
"median": 21.550717420448272,
"minimum": 3.800458970207643,
"maximum": 27.93839234881301
},
"quoted_first_100ms_rms_reduction_db": {
"mean": 17.932329146978255,
"median": 17.504237701162523,
"minimum": 3.147146068931228,
"maximum": 27.10315527948587
},
"first_100ms_peak_above_minus_40_dbfs": {
"tagged": 9,
"quoted": 0
},
"first_activity_under_100ms": {
"tagged": 9,
"quoted": 0
},
"boundary_decay_above_10db": {
"tagged": 8,
"quoted": 0
}
},
"latent_feature_result": "Simple first-frame and first-block RMS/delta ranges overlap between tagged and quoted cases; no scalar latent threshold is justified.",
"subjective_audio_review": {
"reviewed_at": "2026-08-21",
"quoted_cases_reviewed": 10,
"result": "All ten quoted WAVs judged good"
},
"full_video_lip_sync_review_required": true,
"output_directory": "/home/daniel/StoryStudioAssets/H3-output/h3-baselines/audio-dialogue-format-sweep",
"full_report": "/home/daniel/StoryStudioAssets/H3-output/h3-baselines/audio-dialogue-format-sweep/report.json"
}