- Replace fasttext-wheel with underthesea_core>=3.3.0 as core dependency
- Move fasttext-wheel and numpy to dev dependencies (benchmark only)
- Rewrite benchmark to compare all 5 fasttext libraries
- Update TECHNICAL_REPORT.md with full benchmark results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add benchmark_fasttext.py for comparing Rust vs C++ FastText performance
- Add uv.lock for reproducible dependency resolution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add TECHNICAL_REPORT.md documenting the pure Rust FastText inference
implementation: architecture, correctness verification (100% match vs
C++ fasttext), performance benchmarks (2.29x speedup), and bugs found
- Add fasttext-wheel and numpy dependencies to pyproject.toml
- Configure hatch wheel build packages
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Initial project setup for Radar-1 language detection model
