text
https://github.com/pytorch/text
Python
Models, data loaders and abstractions for language processing, powered by PyTorch
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 supported2 Subscribers
Add a CodeTriage badge to text
Help out
- Issues
- Torch Text Transform Documentation Mismatch
- UTF-8 error with testing set of `torchtext.datasets.Multi30k(language_pair=("de", "en"))`.
- how to run this code
- Confusing docs for build_vocab_from_iterator
- One of the three datasets returned by Multi30k seems to be bugged.
- Updates the URL of the character n-gram embeddings in vectors.py
- torchtext 0.16.0 wheels are missing for aarch64 linux platform
- Declaring _MapStyleDataset inside function makes it unpicklable
- CharBPETokenizer docs not rendering correctly
- Link to the original CLIP Tokenizer file needs to be updated in [torchtext.transforms.CLIPTokenizer]
- Docs
- Python not yet supported