pretrained_path is not defined when training from scratch (python train.py -c config.toml)

[ghosthunterk]

After I added the pretrained_path manually in trainer.py it seems to work fine, is this a bug or am I doing something wrong?

[khanld]

By default i use the pretrained wav2vec2-base to init the model architecture and its pretrained weights. The pretrained_path is needed