| | |
|---|
| | | # for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob |
|---|
| | | njob=5 |
|---|
| | | train_cmd=utils/run.pl |
|---|
| | | infer_cmd=utils/run.pl |
|---|
| | | infer_cmd=utils/run.pl |
|---|
| | | |
|---|
| | | # general configuration |
|---|
| | | feats_dir="../DATA" #feature output dictionary |
|---|
| | | exp_dir="." |
|---|
| | | lang=zh |
|---|
| | | token_type=char |
|---|
| | | type=sound |
|---|
| | | scp=wav.scp |
|---|
| | | speed_perturb="0.9 1.0 1.1" |
|---|
| | | stage=0 |
|---|
| | | stop_stage=5 |
|---|
| | | |
|---|
| | | # feature configuration |
|---|
| | | feats_dim=80 |
|---|
| | | nj=64 |
|---|
| | | |
|---|
| | | # data |
|---|
| | | raw_data=/nfs/zhifu.gzf/wenetspeech_proc |
|---|
| | | |
|---|
| | | # exp tag |
|---|
| | | tag="exp1" |
|---|
| | | |
|---|
| | | . utils/parse_options.sh || exit 1; |
|---|
| | | |
|---|
| | | # Set bash to 'debug' mode, it will exit on : |
|---|
| | | # -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands', |
|---|
| | | set -e |
|---|
| | | set -u |
|---|
| | | set -o pipefail |
|---|
| | | |
|---|
| | | set=L |
|---|
| | | train_set=train_l |
|---|
| | | valid_set=dev |
|---|
| | | test_sets="dev test_net test_meeting" |
|---|
| | | |
|---|
| | | asr_config=conf/train_asr_conformer.yaml |
|---|
| | | model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}" |
|---|
| | | |
|---|
| | | inference_config=conf/decode_asr_transformer_5beam.yaml |
|---|
| | | inference_asr_model=valid.acc.ave_10best.pb |
|---|
| | | |
|---|
| | | # you can set gpu num for decoding here |
|---|
| | | gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default |
|---|
| | | ngpu=$(echo $gpuid_list | awk -F "," '{print NF}') |
|---|
| | | |
|---|
| | | if ${gpu_inference}; then |
|---|
| | | inference_nj=$[${ngpu}*${njob}] |
|---|
| | | _ngpu=1 |
|---|
| | | else |
|---|
| | | inference_nj=$njob |
|---|
| | | _ngpu=0 |
|---|
| | | fi |
|---|
| | | |
|---|
| | | if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then |
|---|
| | | echo "For downloading data, please refer to https://github.com/wenet-e2e/WenetSpeech." |
|---|
| | | exit 0; |
|---|
| | | fi |
|---|
| | | |
|---|
| | | if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then |
|---|
| | | echo "stage 0: Data preparation" |
|---|
| | | # Data preparation |
|---|
| | | # local/data.sh --set ${set} --nj $nj --data_dir $feats_dir --WENETSPEECH $raw_data --train_cmd $train_cmd |
|---|
| | | mkdir $feats_dir/data |
|---|
| | | mv $feats_dir/$train_set $feats_dir/data/$train_set |
|---|
| | | for x in $test_sets; do |
|---|
| | | mv $feats_dir/$x $feats_dir/data/ |
|---|
| | | done |
|---|
| | | fi |
|---|
| | | |
|---|
| | | if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then |
|---|
| | | 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 |
|---|
