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 can I parallelize generation of a sharded dataset?
- The inconsistency of Wav2VecFeatureExtractor in unsupervised wav2vec
- Fix typo "deacy"
- If I changed data set, how can I use the parameter "--finetune-from-model"?
- Improve speech recognition for Names and Addresses for wav2vec2.0
- Planning on releasing `fairseq_multilingual_entity_disambiguation` or `mbart.cc100` to HuggingFace hub?
- Position embedding does not support one-hot input
- transformer_layer.py: Could not cast value of type NoneType to bool
- why we use fairseq preprocess to generate bin file ?
- 'dict' object has no attribute 'task' while decoding the language model
- Docs
- Python not yet supported