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
- Unrecognized arguments when attempting to train FastSpeech2 model
- Original VCTK dataset download no longer supported in torchaudio.datasets
- Error Loading Downloaded Hubert Finetuned ASR
- Can't replicate Simultaneous Machine Translation results [missing parameters & bugs]
- enables audio padding rather than cropping for HuBERT finetuning and decoding. Also fixes the issue that the decoding results are non-deterministic due to random audio cropping
- fairseq-train: error: unrecognized arguments when run speech_to_text example
- Got empty batch when using multiple gpus resuming from a checkpoint
- 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?
- Docs
- Python not yet supported