Skip to content

Issues: facebookresearch/fairseq

fairseq v2
#4493 opened Jun 15, 2022 by cbalioglu
Open 6
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.

Sign up for GitHub

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

590 Open 2,871 Closed
590 Open 2,871 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

how to get higher evaluate wmt14 blue needs triage question
#4559 opened Jul 9, 2022 by tjshu
Need help with Hindi Dict in wav2vec2 needs triage question
#4558 opened Jul 9, 2022 by MrityunjoyS
NLLB inference time model loading fails due to inconsistent vocabulary size needs triage question
#4557 opened Jul 8, 2022 by pluiez
4
fp16 bug about grad_norm computation (resulting in min loss scale reached) bug needs triage
#4555 opened Jul 8, 2022 by flycser
Do any fairseq CLI's support forced decoding? needs triage question
#4552 opened Jul 7, 2022 by erip
2
不知道怎么形容，但是NLLB 200 demo所展示的，翻译为简体中文的效果真的太差劲了。 bug needs triage
#4548 opened Jul 7, 2022 by cnmade
No documentation on how use nllb documentation needs triage
#4547 opened Jul 6, 2022 by Suhail
8
Missing West Flemish (Belgian Flemish) language in NLLB needs triage question
#4546 opened Jul 6, 2022 by giyaseddin
Error When fine-tuning from others model.bin : File "~/fairseq/fairseq/checkpoint_utils.py", line 581, in _upgrade_state_dict {"criterion_name": "CrossEntropyCriterion", "best_loss": state["best_loss"]} KeyError: 'best_loss' bug needs triage
#4541 opened Jul 6, 2022 by muhammed-saeed
Generating with MBART50 not working bug needs triage
#4538 opened Jul 5, 2022 by MathieuGrosso
How to generate back translation pairs with monolingual data needs triage question
#4537 opened Jul 5, 2022 by tianshuailu
1
Upload a model only once & translate in any lang pair as much as possible needs triage question
#4536 opened Jul 5, 2022 by molokanov50
3
Data2Vec: missing lm_head in text model bug needs triage
#4535 opened Jul 4, 2022 by stefan-it
1
Data2Vec: error when loading own pretrained model bug needs triage
#4534 opened Jul 4, 2022 by stefan-it
3
Error in loading state_dict M2M100 during finetuning bug needs triage
#4533 opened Jul 4, 2022 by MathieuGrosso
5
Problem with torch version detection bug needs triage
#4532 opened Jul 4, 2022 by stefan-it
No module named 'npy_append_array' needs triage question
#4531 opened Jul 4, 2022 by 646312715
3
Still get a collapse result from wav2vec2 needs triage question
#4530 opened Jul 4, 2022 by andylida
Why FSDP is much slower than normal data Parallel? needs triage question
#4529 opened Jul 1, 2022 by SefaZeng
5
I really want to know how to increase the speed of fairseq-generate needs triage question
#4528 opened Jun 30, 2022 by kkeleve
6
How to reproduce the speech data2vec result? needs triage question
#4527 opened Jun 30, 2022 by yangjiabupt
1
Make some phrases/keywords in the sentence non-translatable needs triage question
#4526 opened Jun 30, 2022 by drone1111
'TH/TH.h' file not found error for PyTorch>=1.11 bug needs triage
#4525 opened Jun 29, 2022 by freewym
How to finetune wmt on your own data needs triage question
#4523 opened Jun 29, 2022 by tatiana-iazykova
6
Trying to convert the model to TorchScript fails in 0.12.2 bug needs triage
#4518 opened Jun 28, 2022 by naor2013
ProTip! What’s not been updated in a month: updated:<2022-06-09.