Is this package actively maintained? If not, @makcedward would you consider some sort of way for someone to take over ownership of the project from you? I have been making improvements to this package locally, but have not opened any PRs because I see that no PRs have been accepted upwards of a year...

Hi, I'm using an M1 Mac Pro and wanted to use the ContextualWordEmbsAug class for some data augmentation. Torch can run on Apple's GPUs that have the device name 'mps', but it has to be initialized correctly. There has to be an issue with this, compared to running on a 'cuda' device, as in the Langu...

I am using this package for the first time, and I was wondering whether there are any recommended augmenters or steps for augmenting long documents. Thanks!

I ran thru the lambada-train_model.ipynb example on my data, and got the tokenizer error The tokenizer class you load from this checkpoint is 'RobertaTokenizer'. The class this function is called from is 'GPT2Tokenizer'. There is no mention of tokenizer in any of the call parameters. How did this...

Hello 👋 I tried using ContextualWordEmbsAug using the xlm-roberta-base model but it seems to be not supported. I needed it to do augmentation on a language that is not available in the bert-base-multilingual-uncased model aug = naw.ContextualWordEmbsAug(model_path='xlm-roberta-base', aug_p=0.1) is t...

In the docs notebook change_log.ipynb, it shows that it's possible to pass include_detail=True when creating augmentations. However, none of the augmentations I've tried this with support directly passing include_detail=True in the constructor. The API docs, e.g. for KeyboardAug here also show inclu...

When I try to run this code: #augment data import importlib import os import nltk os.environ["MODEL_DIR"] = '../model' import nlpaug.augmenter.char as nac import nlpaug.augmenter.word as naw import nlpaug.augmenter.sentence as nas import nlpaug.flow as nafc from nlpaug.util import Action aug = naw...

nlpaug version: 1.1.11 Mac OS import nlpaug.augmenter.word as naw text = 'The quick brown fox jumped over the lazy dog' back_translation_aug = naw.BackTranslationAug(from_model_name='facebook/wmt19-en-ru', to_model_name='facebook/wmt19-ru-en',batch_size=2,force_reload=True) print(back_translation_a...

Hi @makcedward , is there any document which mentions about different parameters used inside augmenter function and a short description what these parameters does? Like : [aug_char_min=1, aug_char_max=10, aug_char_p=0.3, aug_word_p=0.3, aug_word_min=1, aug_word_max=10, stopwords=None, tokenizer=None...