modify paraformer train doc (#1427)

seanzhang-zhichen

2024-03-05 9595a9432fadfbdacd4e6897f6b9a83957699558

 examples/industrial_data_pretraining/paraformer/finetune_from_local.sh

@@ -5,6 +5,8 @@

workspace=`pwd`

echo "current path: ${workspace}" # /xxxx/funasr/examples/industrial_data_pretraining/paraformer

# download model
local_path_root=${workspace}/modelscope_models
mkdir -p ${local_path_root}
@@ -17,25 +19,32 @@
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')

# data dir, which contains: train.json, val.json
data_dir="/Users/zhifu/funasr1.0/data/list"

## 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
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
python -m funasr.datasets.audio_datasets.scp2jsonl \
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${train_data}"

python -m funasr.datasets.audio_datasets.scp2jsonl \
++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${val_data}"


tokens="${local_path}/tokens.json"
cmvn_file="${local_path}/am.mvn"

# exp output dir
output_dir="/Users/zhifu/exp"
# output dir
output_dir="./outputs"
log_file="${output_dir}/log.txt"

config="config.yaml"
config_name="config.yaml"

init_param="${local_path}/model.pt"

@@ -47,7 +56,7 @@
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
--config-path "${local_path}" \
--config-name "${config}" \
--config-name "${config_name}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++tokenizer_conf.token_list="${tokens}" \
@@ -57,5 +66,6 @@
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=20 \
++optim_conf.lr=0.0002 \
++train_conf.log_interval=1 \
++init_param="${init_param}" \
++output_dir="${output_dir}" &> ${log_file}