petite-difference-challenge.../2-preproc-classifier.sh

20 lines
435 B
Bash
Executable File

#!/usr/bin/env bash
set -e
set -x
TEXT=data/
fairseq-preprocess \
--only-source --nwordssrc 50000 \
--trainpref $TEXT/train.txt \
--validpref $TEXT/valid.txt \
--destdir data-bin/classifier-spm-bpe/input0 \
--workers 8
fairseq-preprocess \
--only-source \
--trainpref $TEXT/train/expected.tsv \
--validpref $TEXT/dev-0/expected.tsv \
--destdir data-bin/classifier-spm-bpe/label \
--workers 8