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 convert model trained with QuantNoise to quantized model runnable on CPU only?
- Unable to do inference
- Textless_nlp / gslm: Which CPC embedding should I use in order to use the pretrained k-means model?
- Beam search "cands_to_ignore" is not used correctly.
- Too low BLEU score in reproducing simultaneous speech translation (MuST-C en-de)
- Bidirectional translation with different datasets
- ADAM KeyError: 'max_exp_avg_sq' when further pretraining XLSR 53 on Portuguese Data
- For `FileAudioDataset`, allow manifests to specify short segments of longer audio files
- calculating cer along with wer in infer.py
- Textless NLP: missing tacotron2 training script for GSLM
- Docs
- Python not yet supported