theamato

TypeError: forward() missing 1 required positional argument: 'prev_output_tokens'

3

## ❓ Questions and Help #### What is your question? When trying to fine tune cross attention parameters for mBART, I get this error in the beginning of epoch 1:...

Corpus alignment for Arabic and English

1

I'm wondering if Bleualign can be used for corpus alignment of Arabic and English texts? Or will the fact that Arabic is read from right to left affect performance?

Fine tuning opus nmt ar-en using my own dataset

1

Hi, I want to fine tune the opus nt ar-en model using my own dataset, but I'm not sure what type of files my training data should be in? In...

overlaps without test files?

1

Pherhaps silly quastion, but in the demo, it seems like you create the files with the overlapping sentences with the dev and the test files. In my case, I just...

Are you considering adding a feature that allows you to specify your own fine-tuned opus-mt-model? It would be hugely helpful.

Hi, I'm trying to align an Arabic-English text corpus by using the following command: `src/hunalign/hunalign -text -hand=hand_align_file dict.txt ar.txt en.txt`. I don't have a dictionary, so dict.txt is an empty...

TypeError: forward() missing 1 required positional argument: 'prev_output_tokens'

1

Hi, When running `finetune-mbart-on-transaltion_embed+xattn.sh` I get the error `TypeError: forward() missing 1 required positional argument: 'prev_output_tokens' in the beginning of epoch 1.` When checking the dictionary that is passed into...