E2E Keyword Spotting v3 Assets

What is included

• best_kws12_v2_cpu_baseline.pt: our own detector checkpoint for the stable CPU baseline
• keyword_calibration_v2_cpu_baseline.json: keyword calibration for that checkpoint
• release_summary_v3.json: cleaned release summary used by the public README
• self_benchmark_v3.json: self-benchmark comparison table used by the public README

Important note about v3

• our detector gate/runtime packaging from this repository
• upstream Hugging Face models superb/wav2vec2-base-superb-ks and MIT/ast-finetuned-speech-commands-v2
• our local mapping, calibration, and realtime validation logic

• our own reusable baseline checkpoint
• the cleaned release metrics
• the metadata needed to understand the v3 public result

Result snapshot

• offline worst-class precision: 95.44%
• offline worst-class recall: 95.38%
• unknown-to-target rate: 0.43%