o 2wi @sddlZddlmZddlmZmZddlmZeje dddej dej ddd d ej d e d ej d d e edddej ddedddded ededefddZdS)N)prepare) NSC_PARTS prepare_nsc)PathlikeT) show_default)context_settings corpus_dir)existsdir_okay)type output_dirz-pz--dataset-partPART3_SameCloseMicz$Which part of NSC should be prepared)r defaulthelpz-jz --num-jobszBHow many threads to use (can give good speed-ups with slow disks). dataset_partnum_jobscCst||||ddS)u@  This is a data preparation recipe for the National Corpus of Speech in Singaporean English. CORPUS_DIR: root directory that contains all NSC shared folder. Eg. ├── IMDA - National Speech Corpus │ ├── LEXICON │ ├── PART1 │ ├── PART2 │ └── PART3 ├── IMDA - National Speech Corpus - Additional │ └── IMDA - National Speech Corpus (Additional) │ ├── PART4 │ ├── PART5 │ └── PART6 )rr rN)r)rr rrrY/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/lhotse/bin/modes/recipes/nsc.pynscs! r)clicklhotse.bin.modesrlhotse.recipes.nscrr lhotse.utilsrcommanddictargumentPathoptionChoiceintstrrrrrrs,  (