使用speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型FunASR/examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh进行finetune报错

[D1ner-che]

Notice: In order to resolve issues more efficiently, please raise issue following the template.
（注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）

❓ Questions and Help

Before asking:

1. search the issues.
2. search the docs.

What is your question?

使用speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型FunASR/examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh进行finetune报错

Code

my finetune_from_local.sh

Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.

MIT License (https://opensource.org/licenses/MIT)

method2, finetune from local model

workspace=pwd

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

download model

local_path_root=${workspace}/modelscope_models
mkdir -p ${local_path_root}
local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
git clone https://www.modelscope.cn/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}

which gpu to train or finetune

export CUDA_VISIBLE_DEVICES="0"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')

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

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"

output dir

output_dir="./outputs"
log_file="${output_dir}/log.txt"

config_name="config.yaml"

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

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

torchrun
--nnodes 1
--nproc_per_node ${gpu_num}
../../../funasr/bin/train.py
--config-path "${local_path}"
--config-name "${config_name}"
++train_data_set_list="${train_data}"
++valid_data_set_list="${val_data}"
++tokenizer_conf.token_list="${tokens}"
++frontend_conf.cmvn_file="${cmvn_file}"
++dataset_conf.batch_size=32
++dataset_conf.batch_type="example"
++dataset_conf.num_workers=4
++train_conf.max_epoch=20
++optim_conf.lr=0.0002
++train_conf.log_interval=1
++init_param="${init_param}"
++output_dir="${output_dir}" &> ${log_file}

What have you tried?

What's your environment?

• OS (e.g., Linux):ubuntu22.04
• FunASR Version (e.g., 1.0.0):1.0.15
• ModelScope Version (e.g., 1.11.0):1.13.1
• PyTorch Version (e.g., 2.0.0):2.1.3
• How you installed funasr (pip, source):pip
• Python version:
• GPU (e.g., V100M32)V100M32
• CUDA/cuDNN version (e.g., cuda11.7):12.1.0
• Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
• Any other relevant information:

[LauraGPT]

Ok, we would fix it soon.

[LauraGPT]

Bug has been fixed. Please ref to the docs:
https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/tutorial/README_zh.md