cuda

On 33 vertical Japanese pages (21k chars, exact ground truth), dots.ocr-1.5 had 1.27% CER, LightOnOCR-3-4B 2.59%, chandra-ocr-2 10.96% (repetition loops; turns small kana っ into つ). LightOnOCR-3-1B ships mis-keyed weights and 0.8B ships use_cache=false.

faster-whisper fails at the first GPU compute with "Library libcublas.so.12 is not found" because the ctranslate2 wheel is built for CUDA 12 and the system has CUDA 13. Install nvidia-cublas-cu12 and nvidia-cudnn-cu12 into the venv and set LD_LIBRARY_PATH in a wrapper before Python starts.