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
- using a Sampler() with Iterator()
- Need makedirs call for .vector_cache when path to custom embeddings is passed to Vectors init
- How exactly FastText and CharNGram embedding work in Torchtext
- IMDB data with spaCy loads much slower than other datasets
- torchtext.experimental is not unable to install via nighly build version
- `CLIPTokenizer` always ignores the first line in `bpe_merges`
- `CLIPTokenizer` should output tensors in it's `forward` function rather than lists of numbers in str form
- Separate object construction from file reading
- How to build pytorch text with system third_party libraries?
- Specified Field dtype <torchtext.legacy.data.pipeline.Pipeline object at ...> can not be used with use_vocab=False because we do not know how to numericalize it.
- Docs
- Python not yet supported