| | |
|---|
| | | workspace=`pwd` |
|---|
| | | |
|---|
| | | # which gpu to train or finetune |
|---|
| | | export CUDA_VISIBLE_DEVICES="0" |
|---|
| | | export CUDA_VISIBLE_DEVICES="0,1" |
|---|
| | | gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}') |
|---|
| | | |
|---|
| | | # model_name from model_hub, or model_dir in local path |
|---|
| | | |
|---|
| | | ## option 1, download model automatically |
|---|
| | | model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" |
|---|
| | | model_name_or_model_dir="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope" |
|---|
| | | model_name_or_model_dir="iic/SenseVoiceCTC" |
|---|
| | | |
|---|
| | | ## option 2, download model by git |
|---|
| | | #local_path_root=${workspace}/modelscope_models |
|---|
| | | #mkdir -p ${local_path_root}/${model_name_or_model_dir} |
|---|
| | |
|---|
| | | |
|---|
| | | |
|---|
| | | # data dir, which contains: train.json, val.json |
|---|
| | | data_dir="../../../data/list" |
|---|
| | | |
|---|
| | | train_data="${data_dir}/train.jsonl" |
|---|
| | | val_data="${data_dir}/val.jsonl" |
|---|
| | | |
|---|
| | | # generate train.jsonl and val.jsonl from wav.scp and text.txt |
|---|
| | | scp2jsonl \ |
|---|
| | | ++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \ |
|---|
| | | ++data_type_list='["source", "target"]' \ |
|---|
| | | ++jsonl_file_out="${train_data}" |
|---|
| | | |
|---|
| | | scp2jsonl \ |
|---|
| | | ++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \ |
|---|
| | | ++data_type_list='["source", "target"]' \ |
|---|
| | | ++jsonl_file_out="${val_data}" |
|---|
| | | |
|---|
| | | train_data=${workspace}/data/train_example.jsonl |
|---|
| | | val_data=${workspace}/data/val_example.jsonl |
|---|
| | | |
|---|
| | | # exp output dir |
|---|
| | | output_dir="./outputs" |
|---|
| | | log_file="${output_dir}/log.txt" |
|---|
| | | |
|---|
| | | deepspeed_config=${workspace}/../../ds_stage1.json |
|---|
| | | |
|---|
| | | mkdir -p ${output_dir} |
|---|
| | | echo "log_file: ${log_file}" |
|---|
| | | |
|---|
| | | deepspeed_config=${workspace}../../ds_stage1.json |
|---|
| | | |
|---|
| | | DISTRIBUTED_ARGS=" |
|---|
| | | --nnodes ${WORLD_SIZE:-1} \ |
|---|
| | | --nproc_per_node $gpu_num \ |
|---|
| | | --node_rank ${RANK:-0} \ |
|---|
| | | --master_addr ${MASTER_ADDR:-127.0.0.1} \ |
|---|
| | | --master_port ${MASTER_PORT: 26669} |
|---|
| | | --master_port ${MASTER_PORT:-26669} |
|---|
| | | " |
|---|
| | | |
|---|
| | | echo $DISTRIBUTED_ARGS |
|---|
| | | |
|---|
| | | # funasr trainer path |
|---|
| | | train_tool=`dirname $(which funasr)`/train_ds.py |
|---|
| | | |
|---|
| | | torchrun $DISTRIBUTED_ARGS \ |
|---|
| | | ../../../funasr/bin/train_ds.py \ |
|---|
| | | ${train_tool} \ |
|---|
| | | ++model="${model_name_or_model_dir}" \ |
|---|
| | | ++train_data_set_list="${train_data}" \ |
|---|
| | | ++valid_data_set_list="${val_data}" \ |
|---|
| | | ++dataset="SenseVoiceDataset" \ |
|---|
| | | ++dataset_conf.IndexDSJsonl="IndexDSJsonl" \ |
|---|
| | | ++dataset_conf.data_split_num=1 \ |
|---|
| | | ++dataset_conf.batch_sampler="BatchSampler" \ |
|---|
| | | ++dataset_conf.batch_size=6000 \ |
|---|
| | |
|---|
| | | ++train_conf.use_deepspeed=false \ |
|---|
| | | ++train_conf.deepspeed_config=${deepspeed_config} \ |
|---|
| | | ++optim_conf.lr=0.0002 \ |
|---|
| | | ++output_dir="${output_dir}" #&> ${log_file} |
|---|
| | | ++output_dir="${output_dir}" &> ${log_file} |
|---|
