67 lines
2.1 KiB
Bash
67 lines
2.1 KiB
Bash
|
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
|
||
|
|
# MIT License (https://opensource.org/licenses/MIT)
|
||
|
|
|
||
|
|
# method1, finetune from model hub
|
||
|
|
|
||
|
|
# which gpu to train or finetune
|
||
|
|
export CUDA_VISIBLE_DEVICES="0,1"
|
||
|
|
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||
|
|
|
||
|
|
# model_name from model_hub, or model_dir in local path
|
||
|
|
|
||
|
|
## option 1, download model automatically
|
||
|
|
model_name_or_model_dir="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
|
||
|
|
|
||
|
|
|
||
|
|
## option 2, download model by git
|
||
|
|
#local_path_root=${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 \
|
||
|
|
--nproc_per_node ${gpu_num} \
|
||
|
|
../../../funasr/bin/train.py \
|
||
|
|
++model="${model_name_or_model_dir}" \
|
||
|
|
++model_revision="${model_revision}" \
|
||
|
|
++train_data_set_list="${train_data}" \
|
||
|
|
++valid_data_set_list="${val_data}" \
|
||
|
|
++dataset_conf.batch_size=20000 \
|
||
|
|
++dataset_conf.batch_type="token" \
|
||
|
|
++dataset_conf.num_workers=4 \
|
||
|
|
++train_conf.max_epoch=50 \
|
||
|
|
++train_conf.log_interval=1 \
|
||
|
|
++train_conf.resume=false \
|
||
|
|
++train_conf.validate_interval=2000 \
|
||
|
|
++train_conf.save_checkpoint_interval=2000 \
|
||
|
|
++train_conf.keep_nbest_models=20 \
|
||
|
|
++optim_conf.lr=0.0002 \
|
||
|
|
++output_dir="${output_dir}" &> ${log_file}
|