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
- How to intervene the translation result according to the dictionary
- How to save parts of the texts in target lang inside input text?
- How can I avoid duplicating some tokens during translating?
- How to Qauntize Wav2vec model?
- Translation Quality of NLLB-200(Dense, 3.3B) model is worse as compared to all other models for Japanese & English. Can anyone suggest why?
- Conversion of transformer model to ONNX/ Tracing the model
- Transformer's pad token has non-zero embedding
- Fairseq reinstalls pytorch
- Adds mlflow progress bar
- Why the NLLB 6m model does not add moe layers
- Docs
- Python not yet supported