Done

Good

Latest

feat: 語音登入優化 - 錄音時間調整為3秒 & CNN模組整合

speaker: replace HF/SpeechBrain pipeline with CNN adapter; remove legacy code and audio; reorganize dirs; update deps/Docker/env; add tests; setup Git LFS for model files

fix: add custom.py for ECAPA model and update model

fix: add custom.py for ECAPA model and update model source

fix: add custom.py for ECAPA model and update model sources

fix: add custom.py for ECAPA model and update model source

models: swallow custom.py 404 for speechbrain

Upload 2 files

Bloom Ware 最終修復版本 (Spaces 兼容)