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
- When fine-tuning the MMS model, I encountered NaN loss. How can I solve this issue?
- Make asr_bleu pipeline compatible with 3 lang code
- Default Loss Implementation
- [data2vec] Loss and variance look good but local encoder collapsed
- spelling mistake
- Incorrect url for Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017) in README.md
- unexpected <unk> tokens generated when using XGLM for Chinese-English translation
- MMS-lab and MMS-unlab dataset download
- hydra.errors.MissingConfigException: Could not load model
- Why is wav2vec 2.0 masking prob set to 0.65?
- Docs
- Python not yet supported