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 supported17 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- command line arg parsing for Wav2vec example on TPU
- RuntimeError: Error(s) in loading state_dict for TransformerLanguageModel: Unexpected key(s) in state_dict: "decoder.layer_norm.weight", "decoder.layer_norm.bias".
- [Pytorch Hub] Hub CI is broken with Roberta Model from fairseq
- omegaconf.errors.ConfigKeyError while trying to run hydra_train.py
- The training of BaseLayer pauses at all_to_all_single function
- RoBerta Initialization Error
- wav2vec-u, prepare_audio.sh, wav2vec_extract_features.py, crash when using wav2vec_big_960h.pt
- Poetry installing fairseq fails
- omegaconf.errors.ConfigKeyError: str interpolation key 'model.mask_min_space' not found
- Dictionary entries with `#fairseq:overwrite` are not preserved in dict.txt output from fairseq-preprocess
- Docs
- Python not yet supported