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
- Bug ModuleNotFoundError: No module named 'omegaconf'
- Loss diverging while trying to reproduce product quantization results following fairseq README
- fairseq-hydra-train and --skip-invalid-size-inputs-valid-test
- AttributeError: 'NoneType' object has no attribute 'task'
- Error: KeyError: 'graph_encoder.layers.0.encoder.lin_src.weight'
- AttributeError: 'Index' object has no attribute '_bin_buffer_mmap' during inference with M2M-100
- MissMatch implement in BartTokenizer
- data not found
- Generate top k hypothesis for CTC decoding (infer.py)
- Broken link for pretrain_encoder for speech_text_joint_to_text
- Docs
- Python not yet supported