# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

workspace=`pwd`
export MODELSCOPE_CACHE="/home/boying/IdeaProjects/FunASRxl-0313/models/"
# which gpu to train or finetune
export CUDA_VISIBLE_DEVICES="0"
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-vad-punc_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"

train_data="${data_dir}/train/train.jsonl"
val_data="${data_dir}/val/val.jsonl"

# generate train.jsonl and val.jsonl from wav.scp and text.txt
scp2jsonl \
++scp_file_list='["../../../data/train/train_wav.scp", "../../../data/train/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${train_data}"

scp2jsonl \
++scp_file_list='["../../../data/val/val_wav.scp", "../../../data/val/val_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${val_data}"


# exp output dir
output_dir="/home/boying/IdeaProjects/FunASRxl-0313/exp/paraformer_train"
log_file="${output_dir}/log.txt"

BATCH_SIZE=16
LR=0.0005

deepspeed_config=${workspace}/../../deepspeed_conf/ds_stage1.json

mkdir -p ${output_dir}
echo "log_file: ${log_file}"

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}
"

echo $DISTRIBUTED_ARGS

echo "=========================================="
echo " 开始 FunASR 训练..."
echo "📁 数据目录: $train_data"
echo "💾 输出目录: $output_dir"
echo " 预训练模型: $model_name_or_model_dir"
echo "🎯 Batch Size: $BATCH_SIZE, LR: $LR, Epochs: $MAX_EPOCH"
echo "=========================================="

torchrun $DISTRIBUTED_ARGS \
../../../funasr/bin/train_ds.py \
++model="${model_name_or_model_dir}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset="AudioDataset" \
++dataset_conf.index_ds="IndexDSJsonl" \
++dataset_conf.data_split_num=1 \
++dataset_conf.batch_sampler="BatchSampler" \
++dataset_conf.batch_size="${BATCH_SIZE}"  \
++dataset_conf.sort_size=1024 \
++dataset_conf.batch_type="token" \
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=50 \
++train_conf.log_interval=1 \
++train_conf.resume=true \
++train_conf.validate_interval=2000 \
++train_conf.save_checkpoint_interval=2000 \
++train_conf.keep_nbest_models=20 \
++train_conf.avg_nbest_model=10 \
++train_conf.use_deepspeed=false \
++train_conf.deepspeed_config=${deepspeed_config} \
++optim_conf.lr="${LR}" \
++output_dir="${output_dir}" &> ${log_file}


echo "=========================================="
echo "✅ 训练完成！模型保存在: $output_dir"
echo "=========================================="