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
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
Hello,
Is it possible to use MUSE for completely "new" languages? I am trying to use it for two sign languages and I do not have dictionaries, so I would like to use the unsupervised method. However, if I don't specify the source and target language using --src_lang and --tgt_lang respectively, the languages are set to English and Spanish by default. Is there a workaround to not specify the languages?
If I execute it anyway, after ca. 2h of running it throws the following error:
python3 supervised.py --src_emb ../fastText-0.9.1/sign_lang1.bin --tgt_emb ../fastText-0.9.1/sign_lang2.bin --cuda False --emb_dim 100 :
RuntimeError: invalid argument 1: tensor must have one dimension at /pytorch/aten/src/TH/generic/THTensorEvenMoreMath.cpp:592
I would be very thankful for any help!
Cheers,
Sophia
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hello,
Is it possible to use MUSE for completely "new" languages? I am trying to use it for two sign languages and I do not have dictionaries, so I would like to use the unsupervised method. However, if I don't specify the source and target language using --src_lang and --tgt_lang respectively, the languages are set to English and Spanish by default. Is there a workaround to not specify the languages?
If I execute it anyway, after ca. 2h of running it throws the following error:
I would be very thankful for any help!
Cheers,
Sophia
The text was updated successfully, but these errors were encountered: