-
Notifications
You must be signed in to change notification settings - Fork 6.4k
Issues: facebookresearch/fairseq
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Wav2vec-U Gan train WER UER loss are not satisfactory wav2vec-u wav2vec-u 2.0 gan
needs triage
question
#5572
opened Dec 11, 2024 by
XR1988
Questions about the data used when training Hubert
needs triage
question
#5568
opened Nov 30, 2024 by
duduke37
ImportError: cannot import name 'TOKENIZERS' from 'sacrebleu.tokenizers'
needs triage
question
#5567
opened Nov 28, 2024 by
ALiang36
score calculation in translation_moe
needs triage
question
#5566
opened Nov 20, 2024 by
zhmingzhaung
How do I test it after training?wav2vec2
needs triage
question
#5565
opened Nov 13, 2024 by
lucky-asia
How to use fairseq-hydra-train to finetune Wav2Vec on Intel accelerators?
needs triage
question
#5564
opened Nov 8, 2024 by
vijethk-intel
How to generate hypothese with fconv for DrNMT? (ende)
needs triage
question
#5563
opened Nov 8, 2024 by
123THU
long-standing Bug in Adafactor optimizer if beta1 > 0
bug
needs triage
#5561
opened Oct 30, 2024 by
dxqbYD
Do I need to crop long audio for inference based on pretrained models?
needs triage
question
#5560
opened Oct 29, 2024 by
xuduo18311199384
clarification on additional_special_tokens
needs triage
question
#5559
opened Oct 21, 2024 by
hwang136
wav2vec2-object of type 'NoneType' has no len()
bug
needs triage
#5558
opened Oct 20, 2024 by
Linx3f
How to solve the problem of continuing pre-training the XLSR-53 2B model
bug
needs triage
#5554
opened Oct 15, 2024 by
Learneducn
When I use 8 A40 images to continue pre-training the XLSR-53 2B pre-training model, I always get an error message: Expected is_sm80 to be true, but got false. (could this error message be improved? If so, please report an enhancement request to pytorch) How can I solve this problem?
bug
needs triage
#5553
opened Oct 15, 2024 by
Learneducn
NLLB is unable to translate into a complete long sentence in Chinese.
bug
needs triage
#5549
opened Oct 10, 2024 by
logicvv
ValueError: offset must be non-negative and no greater than buffer length
needs triage
question
#5543
opened Sep 23, 2024 by
LiYixuan727
non-autoregressive transformer training scripts error
needs triage
question
#5541
opened Sep 13, 2024 by
ChloeKiwi
Is there a C++ version of Fairseq based on libtorch
enhancement
help wanted
needs triage
#5540
opened Sep 11, 2024 by
EbanShen
Previous Next
ProTip!
What’s not been updated in a month: updated:<2024-11-24.