Audio-WestlakeU/FS-EEND

The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors". [ICASSP 2024] and "LS-EEND: long-form streaming end-to-end neural diarization with online attractor extraction". [TASLP 2025]

语言：Python · GitHub 星标：192 · Fork：19

话题：end-to-end · frame-wise · long-form · online-inference · pytorch · self-attention · speaker-diarization

在 GitHub 上查看原仓库