Update requirements

Update documentation

Align ASL inference with upstream model

Harden ASL confidence and LLM consistency

Disable Gradio SSR on Space

Remove demo gloss prefill and harden no-detection flow

Expose stepwise ASL debug pipeline

Redesign SignSpeak demo interface

Fix Gradio 6 video input handling

Refactor app into pipeline bricks

Update Gradio launch parameters

Fix llama.cpp JSON parsing before TTS

Update LLM model configuration

Add llama.cpp intent generation and custom UI

Add TTS MVP