#!/bin/bash # To be run from one directory above this script. . ./path.sh text=data/local/lm/text lexicon=data/local/dict/lexicon.txt for f in "$text" "$lexicon"; do [ ! -f $x ] && echo "$0: No such file $f" && exit 1; done # Check SRILM tools if ! which ngram-count > /dev/null; then echo "srilm tools are not found, please download it and install it from: " echo "http://www.speech.sri.com/projects/srilm/download.html" echo "Then add the tools to your PATH" exit 1 fi # This script takes no arguments. It assumes you have already run # aishell_data_prep.sh. # It takes as input the files # data/local/lm/text # data/local/dict/lexicon.txt dir=data/local/lm mkdir -p $dir cleantext=$dir/text.no_oov cat $text | awk -v lex=$lexicon 'BEGIN{while((getline0){ seen[$1]=1; } } {for(n=1; n<=NF;n++) { if (seen[$n]) { printf("%s ", $n); } else {printf(" ");} } printf("\n");}' \ > $cleantext || exit 1; cat $cleantext | awk '{for(n=2;n<=NF;n++) print $n; }' | sort | uniq -c | \ sort -nr > $dir/word.counts || exit 1; # Get counts from acoustic training transcripts, and add one-count # for each word in the lexicon (but not silence, we don't want it # in the LM-- we'll add it optionally later). cat $cleantext | awk '{for(n=2;n<=NF;n++) print $n; }' | \ cat - <(grep -w -v '!SIL' $lexicon | awk '{print $1}') | \ sort | uniq -c | sort -nr > $dir/unigram.counts || exit 1; cat $dir/unigram.counts | awk '{print $2}' | cat - <(echo ""; echo "" ) > $dir/wordlist heldout_sent=10000 # Don't change this if you want result to be comparable with # kaldi_lm results mkdir -p $dir cat $cleantext | awk '{for(n=2;n<=NF;n++){ printf $n; if(n $dir/heldout cat $cleantext | awk '{for(n=2;n<=NF;n++){ printf $n; if(n $dir/train ngram-count -text $dir/train -order 3 -limit-vocab -vocab $dir/wordlist -unk \ -map-unk "" -kndiscount -interpolate -lm $dir/lm.arpa ngram -lm $dir/lm.arpa -ppl $dir/heldout