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 get the perplexity of a single sentence for the custom fairseq pretrained language model?
- Optimize MuST-C preprocessing script
- Wav2vec2_conformer pretrained weights download link is hidden on markdown
- Fix links for conformer weights in wav2vec2 examples readme
- Release 0.12.2 is broken due to #4480 and #4513
- How can I add a histogram of weights to tensorboard
- fix sequence size dtype in token_block_dataset
- Having issues decoding HuBERT: code doesn't load finetune model
- Fix Must-C data preprocessing
- build_dictionary nwords unexpected behavior when real # words < requested nwords
- Docs
- Python not yet supported