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
- prepare_text.sh in wav2vecu has thresholdsrc 2 instead of min_phones
- Cant create Arabic - Hindi translation but can Arabic - French
- Simultaneous (MMA/waitk) inference bug in p_choose
- "KeyError: 'encoder_padding_mask'" during speech_text_joint_task training
- Bug in S2T prep_mustc_data.py with --use-audio-input
- stats[args.best_checkpoint_metric] -> KeyError: 'bleu'
- Bugs and other major issues regarding the MMA code
- layerdrop would cause model training to hang when used with fsdp backend
- Sentencepiece error when running IWSLT21 in Joint Speech Text example
- Cython component could not be correctly compiled in pipenv environment
- Docs
- Python not yet supported