Update requirements

Update README.md

Update documentation

Default ASL detection to WLASL auto backend

Add experimental WLASL I3D backend

Add sliding-window ASL phrase prototype

Expose rejected ASL candidates in intent

Speed up live ASL debug diagnostics

Use single 30-frame ASL upload inference

Draw MediaPipe landmarks in live debug

Align ASL inference with upstream model

Harden ASL confidence and LLM consistency

Disable Gradio SSR on Space

Remove conflicting Gradio pin

Integrate ASL TFLite model assets

Remove demo gloss prefill and harden no-detection flow

Expose stepwise ASL debug pipeline

Redesign SignSpeak demo interface

Fix Gradio 6 video input handling

Document pipeline checks and ASL dependencies

Add brick tests and CLI runners

Refactor app into pipeline bricks

Import ASL video pipeline

Add optional GPU flash attention dependencies

Update Gradio launch parameters

Fix llama.cpp JSON parsing before TTS

Update LLM model configuration

Use Python 3.12 and prebuilt llama.cpp wheel

Add llama.cpp intent generation and custom UI

Add sox system package

Add TTS MVP

initial commit