| | |
|---|
| | | |
|---|
| | | # feature configuration |
|---|
| | | feats_dim=80 |
|---|
| | | sample_frequency=16000 |
|---|
| | | nj=32 |
|---|
| | | speed_perturb="0.9,1.0,1.1" |
|---|
| | | nj=64 |
|---|
| | | |
|---|
| | | # data |
|---|
| | | raw_data= |
|---|
| | |
|---|
| | | feat_train_dir=${feats_dir}/${dumpdir}/train; mkdir -p ${feat_train_dir} |
|---|
| | | if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then |
|---|
| | | echo "stage 1: Feature and CMVN Generation" |
|---|
| | | utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} \ |
|---|
| | | ${feats_dir}/data/${train_set} ${exp_dir}/exp/make_fbank/${train_set} |
|---|
| | | utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set} |
|---|
| | | fi |
|---|
| | | |
|---|
| | | token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt |
|---|
| | |
|---|
| | | echo "</s>" >> ${token_list} |
|---|
| | | utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/train/text | cut -f 2- -d" " | tr " " "\n" \ |
|---|
| | | | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list} |
|---|
| | | num_token=$(cat ${token_list} | wc -l) |
|---|
| | | echo "<unk>" >> ${token_list} |
|---|
| | | vocab_size=$(cat ${token_list} | wc -l) |
|---|
| | | fi |
|---|
| | | |
|---|
| | | # Training Stage |
|---|
