| | |
| | | type=sound |
| | | scp=wav.scp |
| | | speed_perturb="0.9 1.0 1.1" |
| | | stage=3 |
| | | stop_stage=4 |
| | | stage=0 |
| | | stop_stage=5 |
| | | |
| | | # feature configuration |
| | | feats_dim=80 |
| | | nj=64 |
| | | |
| | | # data |
| | | raw_data= |
| | | raw_data=../raw_data |
| | | data_url=www.openslr.org/resources/33 |
| | | |
| | | # exp tag |
| | |
| | | echo "<unk>" >> ${token_list} |
| | | fi |
| | | |
| | | # Training Stage |
| | | # LM Training Stage |
| | | world_size=$gpu_num # run on one machine |
| | | if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then |
| | | echo "stage 3: Training" |
| | | python utils/download_model.py --model_name ${model_name} # download pretrained model on ModelScope |
| | | echo "stage 3: LM Training" |
| | | fi |
| | | |
| | | # ASR Training Stage |
| | | world_size=$gpu_num # run on one machine |
| | | if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then |
| | | echo "stage 4: ASR Training" |
| | | python utils/download_model.py --model_name ${model_name} # download pretrained model on ModelScope |
| | | mkdir -p ${exp_dir}/exp/${model_dir} |
| | | mkdir -p ${exp_dir}/exp/${model_dir}/log |
| | | INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init |
| | |
| | | --data_dir ${feats_dir}/data \ |
| | | --train_set ${train_set} \ |
| | | --valid_set ${valid_set} \ |
| | | --data_file_names "wav.scp,text" \ |
| | | --init_param ${init_param} \ |
| | | --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \ |
| | | --resume true \ |
| | |
| | | fi |
| | | |
| | | # Testing Stage |
| | | if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then |
| | | echo "stage 4: Inference" |
| | | if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then |
| | | echo "stage 5: Inference" |
| | | for dset in ${test_sets}; do |
| | | asr_exp=${exp_dir}/exp/${model_dir} |
| | | inference_tag="$(basename "${inference_config}" .yaml)" |