| | |
|---|
| | | echo "stage 1: Feature and CMVN Generation" |
|---|
| | | utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 0.1 |
|---|
| | | fi |
|---|
| | | |
|---|
| | | token_list=${feats_dir}/data/${lang}_token_list/$token_type/tokens.txt |
|---|
| | | echo "dictionary: ${token_list}" |
|---|
| | | if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then |
|---|
| | | echo "stage 2: Dictionary Preparation" |
|---|
| | | mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/ |
|---|
| | | |
|---|
| | | echo "make a dictionary" |
|---|
| | | echo "<blank>" > ${token_list} |
|---|
| | | echo "<s>" >> ${token_list} |
|---|
| | | echo "</s>" >> ${token_list} |
|---|
| | | utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \ |
|---|
| | | | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list} |
|---|
| | | echo "<unk>" >> ${token_list} |
|---|
| | | fi |
|---|
