请问我们在espnet/egs2/aishell/asr1/下使用，报TypeError: wav2vec2_custom() missing 1 required positional argument: 'ckpt'错误，怎么解决，非常感谢！！！

[MELABIPCAS]

conf/train_asr_conformer_w2v2-base.yaml文件中做修改如下：

network architecture

pretrained model related

freeze_param: [ "frontend.upstream" ]

frontend: s3prl frontend_conf: frontend_conf: upstream: wav2vec2_local upstream_model_config: upstream_ckpt: ./chinese-wav2vec2-base.pt download_dir: ./hub multilayer_feature: true

preencoder: linear preencoder_conf: input_size: 768 # Note: If the upstream is changed, please change this value accordingly. output_size: 80 其中upstream_ckpt:中的选项后面 ./chinese-wav2vec2-base.pt是您们已经训练好的模型，不知道这样修改得对不对？ 非常感谢！！！

[ShChen233]

+1，我也遇到了，请问解决了吗

[fzyfky]

I also encountered similar problems as above when running ./run.sh --stage 11 --stop-stage 11 of espnet/egs2/aishell/asr1. This is part of the yaml file content: `freeze_param:

• "frontend.upstream" frontend: s3prl frontend_conf: frontend_conf: upstream: hubert_local path_or_url: /home/fengky/downloads/chinese-hubert-base/chinese-hubert-base-fairseq-ckpt.pt

  extra_conf:

  #     legacy: true

  download_dir: ./hub multilayer_feature: true

preencoder: linear preencoder_conf: input_size: 1024 # Note: If the upstream is changed, please change this value accordingly. output_size: 80` The following is the error message train.log How can I solve this problem?