Kaldi: Transfer learning

Question

I'm trying to do transfer learning on Kaldi-ASR with a model that has been pretrained on Common Voice, with a custom limited vocabulary dataset. However, I have found the documentation to be quite limited wrt the config file to be provided to egs/commonvoice/s5/steps/online/nnet2/prepare_online_decoding_retrain.sh.

For reference, these are the kind of parameters I have provided

steps/online/nnet2/prepare_online_decoding_transfer.sh --cmd run.pl --config s5/exp/chain/tdnn1a_sp_online/conf/online_cmvn.conf  --stage 0 s5/exp/chain/tdnn1a_sp_online/  s5/data/lang/ s5/exp/chain/tdnn1a_sp_online/ s5/exp/chain/nnet_transfer

The error that I'm currently getting is

steps/online/nnet2/prepare_online_decoding_transfer.sh: no such file <folder-path>/s5/exp/chain/tdnn1a_sp_online/conf/online_nnet2_decoding.conf

Obviously I need to create this file but I don't know how. It would be great if I could have some pointers on how to create this and what config parameters to supply. If any additional information is required, please let me know in the comments.

TIA.