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
- in speech to speech task, the dict.txt file used in target_letter/source_letter/decoder_target_ctc is the same one? only one multitask.yaml is needed?
- Layernorm used in TransformerSentenceEncoderLayer for wav2vec2
- Pretrain roberta model on english wiki corpus dataset
- Librosa required as an additional requirement for p-GSLM
- Why wav2vec2-ctc beam search decoder use logits as AM score?
- Unable to export FairseqIncrementalDecoder to ONNX
- How to get the loss on the test set？
- HuBERT training
- when are the conformer model weights available?
- .ltr, .wrd and lexicon files for train and infer letters model.
- Docs
- Python not yet supported