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
- pre-trained videoclip model for Youcook2?
- License for NLLB-200's tokenizer(SPM-200)
- About Licensing of data2vec 2.0 on vision
- multi-node robert pretraining: "omegaconf.errors.MissingMandatoryValue: Missing mandatory value: model"
- torch.multiprocessing.spawn.ProcessExitedException: process 0 terminated with signal SIGKILL for textless speech to speech translation
- About hubert finetuning
- About extracting the feature of the 12th layer for finetuned hubert model
- Batch size be limited to multiples of 8, causing samples to be missed in train/valid/test dataset
- Some misalignment of data2vec v2 between code and paper
- Pytorch2.0 with fairseq
- Docs
- Python not yet supported