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
- dict' object has no attribute 'task'
- TypeError: object of type 'NoneType' has no len()
- Why the validation loss is often smaller than the training loss?
- letter vocabulary for other language?
- mBART50 Translation/Fine Tuning with Many-to-One Model not working
- [FSDP] Size mismatch when finetuning mBART with `translation_multi_simple_epoch` in FSDP
- hydra train showing issue on cpu
- M2M-100 SentencePiece model produces tokens that are missing on the fixed dictionary
- Unable to train a ASR/ST model on MUST-C data.
- How can I use a language model with wav2vec decoding
- Docs
- Python not yet supported