| | |
|---|
| | | |
|---|
| | | # download model |
|---|
| | | local_path_root=../modelscope_models |
|---|
| | | mkdir -p ${local_path_root} |
|---|
| | | local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch |
|---|
| | | git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path} |
|---|
| | | # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved. |
|---|
| | | # MIT License (https://opensource.org/licenses/MIT) |
|---|
| | | |
|---|
| | | |
|---|
| | | python funasr/bin/train.py \ |
|---|
| | | +model="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \ |
|---|
| | | +token_list="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt" \ |
|---|
| | | +train_data_set_list="data/list/audio_datasets.jsonl" \ |
|---|
| | | +output_dir="outputs/debug/ckpt/funasr2/exp2" \ |
|---|
| | | +device="cpu" |
|---|
| | | # which gpu to train or finetune |
|---|
| | | export CUDA_VISIBLE_DEVICES="0,1" |
|---|
| | | gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}') |
|---|
| | | |
|---|
| | | # model_name from model_hub, or model_dir in local path |
|---|
| | | |
|---|
| | | ## option 1, download model automatically |
|---|
| | | model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" |
|---|
| | | |
|---|
| | | ## option 2, download model by git |
|---|
| | | #local_path_root=${workspace}/modelscope_models |
|---|
| | | #mkdir -p ${local_path_root}/${model_name_or_model_dir} |
|---|
| | | #git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir} |
|---|
| | | #model_name_or_model_dir=${local_path_root}/${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}" |
|---|
| | | |
|---|
| | | |
|---|
| | | # exp output dir |
|---|
| | | output_dir="./outputs" |
|---|
| | | log_file="${output_dir}/log.txt" |
|---|
| | | |
|---|
| | | |
|---|
| | | mkdir -p ${output_dir} |
|---|
| | | echo "log_file: ${log_file}" |
|---|
| | | |
|---|
| | | torchrun \ |
|---|
| | | --nnodes 1 \ |
|---|
| | | --node_rank 0 \ |
|---|
| | | --nproc_per_node ${gpu_num} \ |
|---|
| | | ../../../funasr/bin/train.py \ |
|---|
| | | ++model="${model_name_or_model_dir}" \ |
|---|
| | | ++train_data_set_list="${train_data}" \ |
|---|
| | | ++valid_data_set_list="${val_data}" \ |
|---|
| | | ++dataset_conf.batch_size=20000 \ |
|---|
| | | ++dataset_conf.batch_type="token" \ |
|---|
| | | ++dataset_conf.num_workers=4 \ |
|---|
| | | ++train_conf.max_epoch=50 \ |
|---|
| | | ++train_conf.log_interval=1 \ |
|---|
| | | ++train_conf.resume=false \ |
|---|
| | | ++train_conf.validate_interval=2000 \ |
|---|
| | | ++train_conf.save_checkpoint_interval=2000 \ |
|---|
| | | ++train_conf.keep_nbest_models=20 \ |
|---|
| | | ++train_conf.avg_nbest_model=10 \ |
|---|
| | | ++optim_conf.lr=0.0002 \ |
|---|
| | | ++output_dir="${output_dir}" &> ${log_file} |
|---|
