提交

kongdeqiang

5 天以前 28ccfbfc51068a663a80764e14074df5edf2b5ba

 examples/industrial_data_pretraining/paraformer/finetune.sh

old mode 100644
new mode 100755
@@ -2,15 +2,15 @@
#  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="0,1"
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_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
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
@@ -20,26 +20,29 @@


# data dir, which contains: train.json, val.json
data_dir="../../../data/list"
data_dir="../../../data"

train_data="${data_dir}/train.jsonl"
val_data="${data_dir}/val.jsonl"
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/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++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/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
++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="./outputs"
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

@@ -56,6 +59,14 @@

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}" \
@@ -65,7 +76,7 @@
++dataset_conf.index_ds="IndexDSJsonl" \
++dataset_conf.data_split_num=1 \
++dataset_conf.batch_sampler="BatchSampler" \
++dataset_conf.batch_size=6000  \
++dataset_conf.batch_size="${BATCH_SIZE}"  \
++dataset_conf.sort_size=1024 \
++dataset_conf.batch_type="token" \
++dataset_conf.num_workers=4 \
@@ -78,5 +89,10 @@
++train_conf.avg_nbest_model=10 \
++train_conf.use_deepspeed=false \
++train_conf.deepspeed_config=${deepspeed_config} \
++optim_conf.lr=0.0002 \
++optim_conf.lr="${LR}" \
++output_dir="${output_dir}" &> ${log_file}


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