FastDialogueSidon open-sources 100x faster dialogue separation

HigurashiAI open-sourced FastDialogueSidon, a high-speed version of the two-speaker dialogue separation model DialogueSidon that turns mono audio into 2-channel speech roughly 100x faster on a single GPU with comparable performance.

2026-11-13 ~ 2026-11-13 · 2 related posts

• FastDialogueSidon open-sources 100x faster two-speaker dialogue separation at matching quality — HigurashiAI · 2026-10-27
• FastDialogueSidon released: 2-speaker speech separation ~100x faster with equal quality — kastnerkyle · 2026-11-13