chore: import upstream snapshot with attribution

deltalm/examples/binary_iwslt14.sh

@@ -0,0 +1,15 @@
+set -ex
+
+input_dir=$1
+output_dir=$2
+dict_file=$3
+
+python preprocess.py  \
+    --trainpref $input_dir/train \
+    --validpref $input_dir/valid \
+    --testpref $input_dir/test \
+    --source-lang de --target-lang en \
+    --destdir $output_dir \
+    --srcdict $dict_file \
+    --tgtdict $dict_file \
+    --workers 40

deltalm/examples/evaluate_iwslt14.sh

@@ -0,0 +1,8 @@
+set -ex
+
+data_bin=$1
+save_dir=$2
+
+python generate.py $data_bin \
+    --path $save_dir/checkpoint_best.pt \
+    --batch-size 128 --beam 5 --remove-bpe=sentencepiece

deltalm/examples/prepare_iwslt14.sh

@@ -0,0 +1,97 @@
+#!/usr/bin/env bash
+#
+# Adapted from https://github.com/pytorch/fairseq/blob/master/examples/translation/prepare-iwslt14.sh
+
+mkdir -p $1
+
+cd $1
+
+echo 'Cloning Moses github repository (for tokenization scripts)...'
+git clone https://github.com/moses-smt/mosesdecoder.git
+
+SCRIPTS=mosesdecoder/scripts
+TOKENIZER=$SCRIPTS/tokenizer/tokenizer.perl
+LC=$SCRIPTS/tokenizer/lowercase.perl
+CLEAN=$SCRIPTS/training/clean-corpus-n.perl
+
+URL="http://dl.fbaipublicfiles.com/fairseq/data/iwslt14/de-en.tgz"
+GZ=de-en.tgz
+
+if [ ! -d "$SCRIPTS" ]; then
+    echo "Please set SCRIPTS variable correctly to point to Moses scripts."
+    exit
+fi
+
+src=de
+tgt=en
+lang=de-en
+prep=iwslt14.tokenized.de-en
+tmp=$prep/tmp
+orig=orig
+
+mkdir -p $orig $tmp $prep
+
+echo "Downloading data from ${URL}..."
+cd $orig
+wget "$URL"
+
+if [ -f $GZ ]; then
+    echo "Data successfully downloaded."
+else
+    echo "Data not successfully downloaded."
+    exit
+fi
+
+tar zxvf $GZ
+cd ..
+
+echo "pre-processing train data..."
+for l in $src $tgt; do
+    f=train.tags.$lang.$l
+    tok=train.tags.$lang.tok.$l
+
+    cat $orig/$lang/$f | \
+    grep -v '<url>' | \
+    grep -v '<talkid>' | \
+    grep -v '<keywords>' | \
+    sed -e 's/<title>//g' | \
+    sed -e 's/<\/title>//g' | \
+    sed -e 's/<description>//g' | \
+    sed -e 's/<\/description>//g' | \
+    perl $TOKENIZER -threads 8 -l $l > $tmp/$tok
+    echo ""
+done
+perl $CLEAN -ratio 1.5 $tmp/train.tags.$lang.tok $src $tgt $tmp/train.tags.$lang.clean 1 175
+for l in $src $tgt; do
+    perl $LC < $tmp/train.tags.$lang.clean.$l > $tmp/train.tags.$lang.$l
+done
+
+echo "pre-processing valid/test data..."
+for l in $src $tgt; do
+    for o in `ls $orig/$lang/IWSLT14.TED*.$l.xml`; do
+    fname=${o##*/}
+    f=$tmp/${fname%.*}
+    echo $o $f
+    grep '<seg id' $o | \
+        sed -e 's/<seg id="[0-9]*">\s*//g' | \
+        sed -e 's/\s*<\/seg>\s*//g' | \
+        sed -e "s/\’/\'/g" | \
+    perl $TOKENIZER -threads 8 -l $l | \
+    perl $LC > $f
+    echo ""
+    done
+done
+
+
+echo "creating train, valid, test..."
+for l in $src $tgt; do
+    awk '{if (NR%23 == 0)  print $0; }' $tmp/train.tags.de-en.$l > $prep/valid.$l
+    awk '{if (NR%23 != 0)  print $0; }' $tmp/train.tags.de-en.$l > $prep/train.$l
+
+    cat $tmp/IWSLT14.TED.dev2010.de-en.$l \
+        $tmp/IWSLT14.TEDX.dev2012.de-en.$l \
+        $tmp/IWSLT14.TED.tst2010.de-en.$l \
+        $tmp/IWSLT14.TED.tst2011.de-en.$l \
+        $tmp/IWSLT14.TED.tst2012.de-en.$l \
+        > $prep/test.$l
+done

deltalm/examples/spm_iwslt14.sh

@@ -0,0 +1,16 @@
+set -ex
+
+input_dir=$1
+output_dir=$2
+
+SPM_MODEL=$3
+
+mkdir -p $output_dir
+
+for split in train valid test ;
+do
+    for lang in en de ;
+    do
+        cat $input_dir/$split.$lang | spm_encode --model=$SPM_MODEL --output_format=piece > $output_dir/$split.$lang;
+    done;
+done;

deltalm/examples/train_iwslt14.sh

@@ -0,0 +1,34 @@
+set -ex
+
+data_bin=$1
+save_dir=$2
+PRETRAINED_MODEL=$3
+
+python train.py $data_bin \
+    --save-dir $save_dir \
+    --arch deltalm_base \
+    --pretrained-deltalm-checkpoint $PRETRAINED_MODEL \
+    --share-all-embeddings \
+    --max-source-positions 512 --max-target-positions 512 \
+    --criterion label_smoothed_cross_entropy \
+    --label-smoothing 0.1 \
+    --optimizer adam --adam-betas '(0.9, 0.98)' \
+    --lr-scheduler inverse_sqrt \
+    --lr 1e-4 \
+    --warmup-init-lr 1e-07 \
+    --stop-min-lr 1e-09 \
+    --warmup-updates 4000 \
+    --max-update 400000 \
+    --max-epoch 100 \
+    --max-tokens 1024 \
+    --update-freq 1 \
+    --seed 1 \
+    --log-format simple \
+    --skip-invalid-size-inputs-valid-test \
+    --fp16 \
+    --eval-bleu \
+    --eval-bleu-args '{"beam": 5, "max_len_a": 1.2, "max_len_b": 10}' \
+    --eval-bleu-detok moses \
+    --eval-bleu-remove-bpe=sentencepiece \
+    --eval-bleu-print-samples \
+    --best-checkpoint-metric bleu --maximize-best-checkpoint-metric