Qingyang Zhu

I met the same problem. I guess it throws this error exactly because there is already a `dict.de.txt` file under the corresponding path. If you need to create a different...

Hello @gmryu, your previous answer helped me! But when I have some new self-defined special tokens in the dataset, how to preserve them during the fairseq-preprocess procedure? Or if this...

@gmryu Thank you so much! Your answer cleared most of my problems. I still wonder if there is a way to tell the tokenizer not to split my special tokens....

@gmryu Also if I train from scratch instead of finetuning on a pre-trained model, would there be anything I need to take care of instead of replacing dictionary entries with...

@gmryu Thanks a ton! Nevertheless, I found that `fairseq-preprocess` would generate dict.xx.txt if you didn't specify existing ones. In that case, I guess I don't need to find one, right?...

@gmryu And may I ask for what do we need `[--tokenizer {moses,nltk,space}]` and `--bpe{byte_bpe,bytes,characters,fastbpe,gpt2,bert,hf_byte_bpe,sentencepiece,subword_nmt}]` these parameters in `fairseq-preprocess`?

Yes, one singular value of X should be the square root of an eigenvalue of the covariance matrix of X. I think the problem is fixed in face_edit.py where he...

@gmryu Hi! May I ask what would you suggest me to do if I want to add new inputs (scalars) to the decoder at every time step and use an...

> @martianmartina I guess your solution is not bad. (Though I do not understand what you mean incorporating to target sentences.) > At first glance, I would have a new...

@gmryu I still could need your help and sorry for the confusion I brought about the implementation. It indeed seems weird. I added all my new inputs to the raw...