BlueMagpie-TTS / release_metadata.json
voidful's picture
Document final endpoint policy and rejected speaker-tail pilot
4e11051 verified
Raw
History Blame Contribute Delete
4.96 kB
{
"format": "bluemagpie-pretrained",
"checkpoint": "step_0000049",
"release_status": "selected_stable",
"files": [
"pytorch_model.bin",
"audiovae.pth",
"config.json",
"tokenizer.json",
"tokenizer_config.json"
],
"artifacts": {
"pytorch_model.bin": {
"sha256": "075a553b0981ca0ce8fe77bd9f802fe253bdf0e9f17fbc88fc2b8ae74ad11d3f"
},
"audiovae.pth": {
"sha256": "cc01a2d5d817910f185d959f8bb23d1a5ab80c9a03b7398ac86d7457cb663332"
}
},
"conditioning": {
"production": [
"centroid-only",
"speaker-reference-embedding"
],
"experimental": [
"raw-reference-tokens"
]
},
"inference_policies": {
"standard": {
"scope": [
"centroid-only",
"speaker-reference-embedding"
]
},
"interactive_demo": {
"scope": [
"centroid-only",
"speaker-reference-embedding"
],
"weight_change": false,
"stop_threshold": 0.5,
"stop_late_threshold": 0.05,
"stop_late_start_ratio": 0.75,
"stop_late_full_ratio": 0.95,
"stop_consecutive": 1,
"hard_stop_margin_steps": 1,
"retry_badcase": false,
"candidate_rerank": "none",
"pace_correction": "post_generation_pitch_preserving"
},
"quality_rerank": {
"scope": [
"speaker-reference-embedding-short-medium"
],
"candidate_count": 10,
"fail_closed_on_boundary_fallback": true,
"centroid_status": "not_promoted",
"longform_status": "not_promoted"
}
},
"evaluation": {
"scope": "internal held-out evaluation",
"centroid_only": {
"profile": "controlled_30_texts_5_seeds",
"cer": 0.1537326315659649,
"wer": 0.4148126965626966,
"chars_per_second_median": 4.044117647058823,
"chars_per_second_p95": 4.166666666666667,
"speaker_across_texts_median": 0.4630973200859695,
"speaker_centroid_p10": 0.37282803654670715
},
"speaker_reference_embedding": {
"release_role": "production",
"profile": "controlled_30_texts_5_seeds",
"cer": 0.13387449587449585,
"wer": 0.330523828023828,
"chars_per_second_median": 4.044117647058823,
"chars_per_second_p95": 4.166666666666667,
"duration_cv": 0.045454545454545414,
"speaker_across_texts_median": 0.4557993102947186,
"speaker_reference_p10": 0.3619180113077164
},
"speaker_reference_quality_rerank": {
"release_role": "opt_in_short_medium",
"profile": "controlled_30_texts_10_candidates",
"candidate_pool_cer": 0.09351897921002666,
"candidate_pool_wer": 0.0950508473008473,
"selected_cer": 0.011402486402486402,
"selected_wer": 0.018602693602693603,
"independent_asr_selected_cer": 0.06834166650343122,
"independent_asr_selected_wer": 0.06783609908609908,
"chars_per_second_median": 4.044117647058823,
"chars_per_second_p95": 4.166666666666667,
"early_stop_rate": 0.0,
"overrun_rate": 0.0,
"sentence_final_truncation_rate": 0.0,
"boundary_fallback_count": 0,
"speaker_across_texts_median": 0.5111590030378309,
"speaker_reference_p10": 0.4438544690608978,
"begin_end_speaker_drop_max": 0.029450446367263794
},
"quality_rerank_non_promoted": {
"centroid": "speaker boundary and duration-variance gates failed",
"longform": "one of twelve holdout requests failed the speaker boundary gate"
},
"natural_stop": {
"status": "pace_gate_failed",
"speaker_reference_cer": 0.1285453712953713,
"speaker_reference_p95_chars_per_second": 6.25,
"speaker_reference_early_stop_rate": 0.5066666666666667
},
"longform_chunked_80_no_context": {
"profile": "3_texts_5_seeds_4_independent_processes",
"speaker_reference_target_chars_per_second": 4.0,
"speaker_reference_cer_range": [
0.094041807917406,
0.11895441082043953
],
"speaker_reference_wer_range": [
0.11134638441192352,
0.1314329644985036
],
"speaker_reference_median_chars_per_second_range": [
3.8744796669868715,
3.8864628820960703
],
"speaker_reference_p95_chars_per_second": 3.993055555555556,
"speaker_reference_duration_cv_range": [
0.013068433930598339,
0.023848728609339148
],
"speaker_reference_across_texts_range": [
0.7589647054672242,
0.7714100420475006
],
"speaker_reference_p10_range": [
0.5465801358222961,
0.5569551467895508
],
"speaker_reference_first_last_sentence_drop_p95_range": [
0.01657727062702179,
0.029698908329010003
],
"sentence_final_truncation_rate": 0.0,
"asr_outlier_rate": 0.0,
"chunk_chars": 80,
"continuation_context_sec": 0.0,
"fixed_seed_across_requests": false,
"random_request_seed_reused_across_chunks": true
}
}
}