-
Notifications
You must be signed in to change notification settings - Fork 16
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Missing dictionary file for preprocess.sh #1
Comments
Same question, have you solved this? |
No, I haven't solved it. |
I think it's here. |
Yeah, this is correct. |
Has anyone here found a way to generate the "test.src" file in generate questions section? |
but i can not open the link now, can anyone know how to get the model from other resource |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Dear Alex, thanks for the great work.
When I run the command
./fairseq/scripts/aw/preprocess.sh preprocess
, it raises the error ofFileNotFoundError: [Errno 2] No such file or directory: 'models/fseq/dict.txt'
.I also searched this file in this repository but I cannot find it.
Could you please provide this file?
I also find that the tokenization script uses the BERT tokeniser instead of BART? I would like to ask if these two models use the same tokeniser? Thanks!
The text was updated successfully, but these errors were encountered: