fairseq
https://github.com/facebookresearch/fairseq
Python
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported14 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- Norwegian support in MMS
- About pretraining RoBERTa on custom data
- LID model - list of supported languages and source code
- NameError: name 'BertEmbeddings' is not defined
- Can I use weights of XLM-Roberta LM as embedding of the encoder of the fconv_wmt_en_de for machine translation task instead of random initialization ?
- wav2vec2: Key 'ddp_backend' not in 'DistributedTrainingConfig'
- Issues with CI Workflow Execution and Code Coverage Collection
- Cannot inherit from base config with hydra
- ImportError: cannot import name 'MultiheadAttention' from partially initialized module 'fairseq.modules' (most likely due to a circular import) (/home/jiahui/workspace/nmt/bert_nmt/fairseq/fairseq/modules/__init__.py)
- Error when running fairseq data2vec example
- Docs
- Python not yet supported