Skip to content

v0.1.7-speaker — Auto-tuned diarization

Choose a tag to compare

@yanhuicsdn yanhuicsdn released this 19 Jul 11:08
· 7 commits to main since this release

v0.1.7-speaker — AutoResearch 自动调优版

主要变更

  • AutoResearch 式参数自动调优,33 次试验找到最佳参数组合
  • 参数优化:threshold=0.6, stepRatio=0.15, minSegmentDuration=0.3
  • 新增 --tune 标志,支持对新音频自动调优
  • 说话人识别准确率大幅提升

调优关键发现

参数 旧值 新值
clustering.threshold 0.5 0.6
segmentation.stepRatio 0.2 0.15
embedding.minSegmentDuration 0.5 0.3
segmentation.minDurationOn 0.2 0.0
segmentation.minDurationOff 0.3 0.0
postProcessing.minGapDuration 0.05 0.1

下载

  • ohr-speaker_macOS_arm64.zip — macOS Apple Silicon (M1/M2/M3/M4)