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
- FileExistsError: data-bin/iwslt14.tokenized.de-en/dict.de.txt
- Data load offsets and lengths
- KeyError: 'attn'
- how to generate .tsv and .ltr file when use hubert ???
- SacreBLEU score incorrect due to <<unk>> tokens (different reference length)
- Why newest version fairseq's interactive.py result in bad translation inference , but version 0.8 fairseq can normally inference good result.
- byte_level_bpe data no longer exists
- Roberta torch.hub archive is no longer on GitHub
- FloatingPointError: gradients are Nan/Inf
- Update release versions to support getting-started examples
- Docs
- Python not yet supported