feat: train transformer on HF A10G + heuristic improvements

fix: pin gradio>=4.44.1, modernize typing, clean ruff lint

fix(heuristic): range-based numeric cipher discrimination + Voynich detection

feat(data): add 20 sparse-label synthetic generators; dataset now 90 222 rows

feat(training): add early stopping, cosine LR schedule, and push-to-hub

fix: remove duplicate-tail dead code; harmonise app label vocabulary

feat: expand to 81 ciphers — improved heuristic, 12 new cipher generators, focal-loss training

Improve training: weighted loss, blind eval split, roberta-base defaults, 512 tokens

Fix singleton class crash: normalise wallis_ciphers typo, guard train_test_split

Replace synthetic 8-label dataset with cipher-museum 100k/82-label corpus

Fix Trainer API: tokenizer -> processing_class (transformers 5.x)

Make Space HF-launch-ready: fix boot crash, add solver, expand eval, polish UX

ADA/mobile UI, pytest pythonpath, train_transformer PyArrow fix, enriched Explain Mode

10/10 polish: Compare Mode, Kasiski/Friedman, rich dataset schema, expanded tests/docs

Initial Cipher Detective AI public foundation