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
- Left-padding and right-padding discrepancy for LSTM alignments
- Links in `prepare-iwslt17-multilingual.sh` don't work
- Loading HuBERT pretrained model, dictionaries cannot be properly loaded.
- Preprocess will double-encode bpe-encoded input
- RuntimeError: Error(s) in loading state_dict for Wav2VecCtc, when loading wav2vec2.0 pretrained model
- AttributeError: 'dict' object has no attribute 'replace', when loading vq-wav2vec pretrained model as in the instructions
- Bug in paraphraser example
- Fairseq-train Hangs in a loop of validation and saving checkpoint while using truncated_bptt task
- Is layerdrop working only with --ddp-backend no_c10d?
- checkpoint_wrapper at the first block disabling gradients
- Docs
- Python not yet supported