train update

游雁

2024-03-27 9b4e9cc8a0311e5243d69b73ed073e7ea441982e

 examples/industrial_data_pretraining/paraformer/finetune.sh

@@ -1,27 +1,67 @@

## 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}

## generate jsonl from wav.scp and text.txt
#python -m funasr.datasets.audio_datasets.scp2jsonl \
#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
#++data_type_list='["source", "target"]' \
#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)


# torchrun \
# --nnodes 1 \
# --nproc_per_node 1 \
python funasr/bin/train.py \
+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+model_revision="v2.0.4" \
+train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len_10.jsonl" \
+valid_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len_10.jsonl" \
++dataset_conf.batch_size=64 \
++dataset_conf.batch_type="example" \
++train_conf.max_epoch=2 \
# 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 \
+output_dir="outputs/debug/ckpt/funasr2/exp2"
++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=5 \
++optim_conf.lr=0.0002 \
++output_dir="${output_dir}" &> ${log_file}