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
- Can I use the wav2vec2 base model to train my own dataset which is of 8000 sample rate?
- slow Roberta pretraining from scratch
- fairseq-train: error: unrecognized arguments: --mask-multiple-length 10 --mask-stdev 10
- can we skip flashlight when using fairseqlm LM for decoding for wave2vec?
- Why RoBERTa use both merges.txt and vocab.json at the same time rather than just single vocab.txt like BERT
- Is there any way to speed up while inferencing the model with a Non-GPU environment?
- Loading XLSR53 Model for simple inference test
- Wav2vec2 negtive sampling, little bug
- BPE and wav2vec
- KeyError: 27707 in pytorch 1.7.1 (GeForce RTX 3090)
- Docs
- Python not yet supported