Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of dl-translate

dl-translate - v0.3.2

What's Changed

  • Fix for nllb by @Galoist in https://github.com/xhluca/dl-translate/pull/64

New Contributors

  • @Galoist made their first contribution in https://github.com/xhluca/dl-translate/pull/64

Full Changelog: https://github.com/xhluca/dl-translate/compare/v0.3.1...v0.3.2

- Python
Published by xhluca almost 2 years ago

dl-translate - v0.3.1

What's Changed

  • Update README.md by @xhluca in https://github.com/xhluca/dl-translate/pull/60
  • Make tqdm optional cause it interferes with thread monkey patching in gevent by @ddorian in https://github.com/xhluca/dl-translate/pull/61
  • Update setup.py by @xhluca in https://github.com/xhluca/dl-translate/pull/62

New Contributors

  • @ddorian made their first contribution in https://github.com/xhluca/dl-translate/pull/61

Full Changelog: https://github.com/xhluca/dl-translate/compare/v0.3.0...v0.3.1

- Python
Published by xhluca about 2 years ago

dl-translate - v0.3.1

What's Changed

  • Update README.md by @xhluca in https://github.com/xhluca/dl-translate/pull/60
  • Make tqdm optional cause it interferes with thread monkey patching in gevent by @ddorian in https://github.com/xhluca/dl-translate/pull/61

New Contributors

  • @ddorian made their first contribution in https://github.com/xhluca/dl-translate/pull/61

Full Changelog: https://github.com/xhluca/dl-translate/compare/v0.3.0...v0.3.1

- Python
Published by xhluca about 2 years ago

dl-translate - dl-translate v0.3.0

New

  • NLLB is now available, allowing you to translate up to 200 languages. It is also much faster.
  • Notebook demo for nllb

Changed

  • New minimum version of transformers (4.30+) and PyTorch (2.0+)
  • Modify behavior of _resolve_lang_codes
  • Moved certain hidden functions to utils

Fixed

  • dlt.utils: Changed default for available_languages, get_lang_code_map, available_codes. Previously was incorrectly set to mbart50.

Docs

  • Improved Readme with examples for nllb
  • Removed mentions of readthedocs.io
  • Change language reference to table (previously bullet points)

- Python
Published by xhluca almost 3 years ago

dl-translate - dl-translate v0.2.6

Update readme with link to new docs

- Python
Published by xhluca almost 4 years ago

dl-translate - dl-translate v0.2.5

- Python
Published by xhluca almost 5 years ago

dl-translate - dl-translate v0.2.4

- Python
Published by xhluca almost 5 years ago

dl-translate - dl-translate v0.2.3

- Python
Published by xhluca almost 5 years ago

dl-translate - dl-translate v0.2.2.post1

Enable Zenodo Archiving

This will allow this repo to obtain a DOI. No changes to this repo was made

- Python
Published by xhluca almost 5 years ago

dl-translate - dl-translate v0.2.2

Change languages available in dlt.lang

Changed

  • Docs: Available languages now include "Khmer" (which maps to central khmer)

Fixed

  • dlt.lang will now have all the languages corresponding to m2m100 instead of mbart50

- Python
Published by xhluca about 5 years ago

dl-translate - dl-translate v0.2.1

Fix dlt.TranslationModel.load_obj

Added

  • New tests for saving and loading.

Fixed

  • dlt.TranslationModel.load_obj: Will now work without having to explicitly give the model family.

- Python
Published by xhluca about 5 years ago

dl-translate - dl-translate v0.2.0

Add m2m100 as the new default model to support 100 languages

Added

  • dlt.lang.m2m100 module: Now has variables for over 100 languages, also auto-complete ready. Example: dlt.lang.m2m100.ENGLISH.
  • dlt.utils.available_languages, dlt.utils.available_codes: Now supports argument "m2m100"
  • Available languages for each model family
  • Script and template to generate available languages

Changed

  • [BREAKING] dlt.lang.TranslationModel: A new model parameter called model_family in the initialization function. Either "mbart50" or "m2m100". By default, it will be inferred based on model_or_path. Needs to be explicitly set if model_or_path is a path.
  • [BREAKING] Default model changed to m2m100
  • Docs and readme about mbart50 were reframed to take into account the new model
  • dlt.TranslationModel.translate: Improved docstring to be more general.
  • Tests pertaining to m2m100
  • scripts/generate_langs.py: Renamed, mechanism now changed to loading from json files
  • docs/index.md: Expand the "Usage" and "Advanced" sections
  • README.md: Add acknowledgement about m2m100, significantly trim "Advanced" section, make "Usage" more concise

Fixed

  • dlt.TranslationModel.available_codes() was returning the languages instead of the codes. It will now correctly return the code.

Removed

  • Output type hints for TranslationModel.get_transformers_model and TranslationModel.get_tokenizer
  • [BREAKING] dlt.TranslationModel.bart_model and dlt.TranslationModel.tokenizer are no longer available to be used directly. Please use dlt.TranslationModel.get_transformers_model and dlt.TranslationModel.get_tokenizer instead.

- Python
Published by xhluca about 5 years ago

dl-translate - dl-translate v0.2.0rc1

Add m2m100 as an alternative to mbart50

m2m100 has more languages available (~110) and has also reported their absolute BLEU scores.

Added

  • dlt.lang.m2m100 module: Now has variables for over 100 languages, also auto-complete ready. Example: dlt.lang.m2m100.ENGLISH.
  • dlt.utils.available_languages, dlt.utils.available_codes: Now supports argument "m2m100"

Changed

  • [BREAKING] dlt.lang.TranslationModel: A new model parameter called model_family in the initialization function. Either "mbart50" or "m2m100". By default, it will be inferred based on model_or_path. Needs to be explicitly set if model_or_path is a path.
  • dlt.TranslationModel.translate: Improved docstring to be more general.
  • Tests pertaining to m2m100
  • scripts/generate_langs.py: Renamed, mechanism now changed to loading from json files

Fixed

  • dlt.TranslationModel.available_codes() was returning the languages instead of the codes. It will now correctly return the code.

Removed

  • Output type hints for TranslationModel.get_transformers_model and TranslationModel.get_tokenizer
  • [BREAKING] dlt.TranslationModel.bart_model and dlt.TranslationModel.tokenizer are no longer available to be used directly. Please use dlt.TranslationModel.get_transformers_model and dlt.TranslationModel.get_tokenizer instead.

- Python
Published by xhluca over 5 years ago

dl-translate - dl-translate v0.1.0

Initial Release

This is the initial release of, dl-translate, a deep learning-based translation library built on Huggingface transformers and Facebook's mBART-Large. To install, run: pip install dl-translate

Check out the user guide to get started, or use of the following links:

💻 GitHub Repository 📚 Documentation / Readthedocs 🐍 PyPi project 🧪 Colab Demo / Kaggle Demo

- Python
Published by xhluca over 5 years ago