2024.01.19 微调代码出现问题

[xyx361100238]

🐛 Bug

To Reproduce

Steps to reproduce the behavior (always include the command you ran):

1. Run cmd 'finetune.sh'
2. See error

Code sample

python3 funasr/bin/train.py \ +model="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \ +model_revision="v2.0.2" \ +train_data_set_list="data/list/audio_datasets.jsonl" \ +valid_data_set_list="data/list/audio_datasets.jsonl" \ ++dataset_conf.batch_size=6000 \ ++dataset_conf.num_workers=4 \ ++train_conf.nax_epoch=5 \ +output_dir="outputs" \ +device="cuda"

Expected behavior

Environment

• OS (e.g., Linux):
• FunASR Version (e.g., 1.0.0): 1.0.0
• ModelScope Version (e.g., 1.11.0): 1.11.0
• PyTorch Version (e.g., 2.0.0): 1.13.1
• How you installed funasr (pip, source): source
• Python version: 3.8
• GPU (e.g., V100M32) N3080
• CUDA/cuDNN version (e.g., cuda11.7): 11.6
• Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
• Any other relevant information:

Additional context

[xyx361100238]

这个是曾经的训练过程：

[xyx361100238]

问题依然存在 ，请帮忙查看下

[pengpengzi]

问题依然存在 ，请帮忙查看下 " " 我也遇到了同样的问题，请问解决了吗

[xyx361100238]

没有呢 社区里面也没有反馈

[xyx361100238]

@LauraGPT