Reduce speaker over-segmentation in auto clustering

Restore required Spaces YAML configuration in README

Remove HF YAML frontmatter from README for clean GitHub rendering

Write README as UTF-8 without BOM for HF frontmatter parsing

Fix README Space metadata colorTo value

Rewrite README with clear setup, deployment, and troubleshooting

Add pyannote-first diarization path and tune fallback clustering

Fix stereo duration handling and robust ECAPA model loading

Fix Spaces UI API endpoint default to same-origin

Fix portability, model cache handling, and deploy token safety

Fix LocalStrategy.COPY for speechbrain 1.0.3

Debug from_hparams signature

Fix from_hparams for speechbrain 1.0.3

Add debug endpoint

Fix cache dir for HuggingFace Spaces

Add HuggingFace Spaces configuration

Initial commit: Speaker Diarization System