Joeynmt

- introduced [DistributedDataParallel](https://pytorch.org/tutorials/beginner/dist_overview.html).
- implemented language tags, see [notebooks/torchhub.ipynb](https://github.com/joeynmt/joeynmt/blob/main/notebooks/torchhub.ipynb)
- released a [iwslt14 de-en-fr multilingual model](https://huggingface.co/may-ohta/iwslt14_prompt) (trained using DDP)
- special symbols definition refactoring
- configuration refactoring
- autocast refactoring
- bugfixes
- upgrade to python 3.11, torch 2.1.2
- documentation refactoring

- compatibility with [torch 1.13](https://github.com/pytorch/pytorch/releases/tag/v1.13.1) tested
- [torchhub](https://pytorch.org/hub/) introduced
- bugfixes, minor refactoring ([119](https://github.com/joeynmt/joeynmt/pull/199), [#198](https://github.com/joeynmt/joeynmt/issues/198))

- upgrade to python 3.10, torch 1.12
- replace Automated Mixed Precision from NVIDA's amp to Pytorch's amp package
- replace [discord.py](https://github.com/Rapptz/discord.py) with [pycord](https://github.com/Pycord-Development/pycord) in the Discord Bot demo
- data Iterator refactoring (https://github.com/joeynmt/joeynmt/pull/189, https://github.com/joeynmt/joeynmt/pull/190, https://github.com/joeynmt/joeynmt/pull/191)
- migrate to pytorch's torch.testing.assert_close to check tensors in unittests
- add wmt14 ende / deen benchmark trained with joey v2 from scratch
- bugfixes

Breaking changes:
- upgrade to python 3.9, torch 1.11
- torchtext.legacy dependencies are completely replaced by torch.utils.data
- joeynmt/tokenizers.py: handles tokenization internally (also supports bpe-dropout!)
- joeynmt/datasets.py: loads data from plaintext, tsv, and huggingface's [datasets](https://github.com/huggingface/datasets)
- scripts/build_vocab.py: trains subwords, creates joint vocab
- enhancement in decoding
- scoring with hypotheses or references
- repetition penalty, ngram blocker
- attention plots for transformers
- yapf, isort, flake8 introduced
- bugfixes, minor refactoring