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
- data2vec_text: EMA teacher processes only masked tokens, instead of full sequence.
- pip install fairseq fails on windows 11
- Procedure/recipe for building phoneme recognition system
- Multi-GPU training doesn't work when `--user-dir` specified
- An error when creating ExtractedFeatureDataset for Wav2Vec-U:The `variable` doesn't get updated when skipping samples
- Is there "Linear Transformer" Model in Fairseq.transformers ?
- The result of the fine-tuned model inference is missing the second half and is represented by the symbol"�"
- TypeError: forward() missing 1 required positional argument: 'prev_output_tokens'
- Update get_available_activation_fns to match get_activation_fn
- Dangerous implement of parsers (`fairseq.data.codedataset.parse_manifest`) can cause RCE while parsing a well-constructed evil file.
- Docs
- Python not yet supported