You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have downloaded the pretrained model from icefall. I have tried to finetune the model in zipformer using my own data. It is showing mismatch error. I have attached the error file error.txt
The text was updated successfully, but these errors were encountered:
size mismatch for encoder.encoders.0.layers.0.self_attn_weights.in_proj.weight: copying a param with shape torch.Size([272, 192]) from checkpoint, the shape in current model is torch.Size([544, 192]).
The first thing you have to do is to find out the exact parameters used to train the model that you are using for finetuing.
I solved that error. Can you please tell me this isse?
File "finetune.py", line 1121, in train_one_epoch
cur_grad_scale = scaler._scale.item()
AttributeError: 'GradScaler' object has no attribute '_scale'
I have downloaded the pretrained model from icefall. I have tried to finetune the model in zipformer using my own data. It is showing mismatch error. I have attached the error file
error.txt
The text was updated successfully, but these errors were encountered: