makcedward/nlpaug

Issues

• Using nas.ContextualWordEmbsForSentenceAug with gpt2 or distilgpt2 returns nonsense

  #346 opened 7 months ago by djaszak
  0

• Is support for facebook/bart-base removed in the latest version?

  #345 opened 8 months ago by imranraad07
  0

• Not able to presever the words.

  #344 opened 9 months ago by Opperessor
  0

• Feature Request: Progress bar during augmentation

  #343 opened 9 months ago by bauersimon
  0

• Character Augmenters remove non-breaking spaces before punctuation and insert spaces around apostrophes

  #313 opened 2 years ago by lindsaydbrin
  3

• Can't extract `str` to `Vec` while using nas.ContextualWordEmbsForSentenceAug(model_path='xlnet-base-cased')

  #316 opened 2 years ago by EtherealRise
  2

• instancing more than one naw spelling aug with diferent dict_path doesn't work

  #342 opened a year ago by jhpiedrahitao
  0

• In the documentation it is unclear about the spelling dictionary

  #311 opened 2 years ago by xihajun
  2

• Actively maintained?

  #338 opened a year ago by Ubadub
  3

• Bug on 1.1.11

  #340 opened a year ago by ririya
  0

• Error with English to French Backtranslation

  #339 opened a year ago by alejopaullier96
  0

• UnknownExtra: requests 2.27.1 has no such extra feature 'socks'

  #310 opened 2 years ago by moe-men
  1

• Add link to documentation for supported synonyms for nlpaug.augmenter.word.synonym

  #289 opened 2 years ago by ArtificialTruth
  2

• does `ContextualWordEmbsAug` support XLM-Roberta models

  #334 opened 2 years ago by cmgchess
  1

• TypeError when utilizing GPU on Apple silicon for language models

  #337 opened 2 years ago by BlueJ1
  0

• Augmenting Long Documents

  #336 opened 2 years ago by vc34
  0

• The tokenizer class you load from this checkpoint is 'RobertaTokenizer'

  #335 opened 2 years ago by bhomass
  0

• What is the correct way to specify include_detail=True?

  #333 opened 2 years ago by chanind
  0

• LookupError when trying to augment data with SynonymAug

  #332 opened 2 years ago by moonman239
  0

• RuntimeError: DataLoader worker (pid(s) 3954) exited unexpectedly

  #330 opened 2 years ago by pratikchhapolika
  0

• Short description about different parameters used inside augmenter and what it does?

  #329 opened 2 years ago by pratikchhapolika
  0

• lambada augmenter: The following `model_kwargs` are not used by the model: ['num_workers']

  #326 opened 2 years ago by NhatHoang2002
  2

• Lambada Model giving gibberish output

  #328 opened 2 years ago by Onkar-2803
  0

• Unable to generate new data

  #327 opened 2 years ago by yuchen74
  0

• ContextualWordEmbsAug: extra whitespace before and after punctuaion

  #325 opened 2 years ago by MT010104
  0

• Question: Is there an (easy) way to preserve (trailing) spaces and carriage returns when using `ContextualWordEmbsAug`?

  #323 opened 2 years ago by barseghyanartur
  0

• load_word2vec_format() got an unexpected keyword argument 'no_header'

  #322 opened 2 years ago by Hossein-1991
  0

• Numpy Error

  #320 opened 2 years ago by akhileshrai003
  0

• Coverage of "Data Augmentation using Pre-trained Transformer Models" paper in this library

  #319 opened 2 years ago by kumar-abhishek
  0

• Muti-gpu support

  #318 opened 2 years ago by slvcsl
  0

• Typeerror with ContextualWordEmbsAug

  #317 opened 2 years ago by zhangyaqi20
  1

• `candidates` in `RandomCharAug` is not working as expected

  #315 opened 2 years ago by lindsaydbrin
  0

• Duplicate lines in example

  #312 opened 2 years ago by ziqing-huang
  0

• Process finished with exit code 132 (interrupted by signal 4: SIGILL)

  #309 opened 2 years ago by alaa-maverick
  0

• UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

  #308 opened 2 years ago by NitishOritro
  0

• AbstSummAug doesn't have num_beam parameter

  #307 opened 2 years ago by Oleg-Litvinov-EPAM
  0

• I guess this is a bug...

  #295 opened 2 years ago by beyondguo
  1

• Util for downloading from Google Drive no longer works

  #301 opened 2 years ago by MarkusSagen
  0

• Consistent data type (list) for char augmenters

  #302 opened 2 years ago by fratambot
  1

• issue with the input length in "ContextualWordEmbsForSentenceAug" model

  #285 opened 3 years ago by musaalamparvez
  1

• Use NLP with dataframes and labels

  #286 opened 3 years ago by haris525
  1

• Unknown Token interfering with stopwords with word augmenter

  #287 opened 3 years ago by vera-bernhard
  0

• How to generate more than 1 augmented samples using Back-Translation method?

  #288 opened 3 years ago by beyondguo
  1

• 运行lambada.py出错

  #291 opened 2 years ago by bairan1
  1

• 404 Client Error: Repository Not Found for url: https://huggingface.co/fHelsinki-NLP/opus-mt-en-zh/resolve/main/config.json

  #293 opened 2 years ago by hjing100
  1

• Don't change specified words.

  #296 opened 2 years ago by xxupiano
  4

• How to specify max_length on the input text in BackTranslationAug

  #297 opened 2 years ago by JohnGiorgi
  0

• Using Offline models

  #299 opened 2 years ago by chechu-arias
  1

• Using custom Tensorflow transformer from HuggingFace

  #292 opened 3 years ago by sandstorm12
  1

• Issue with Contextual Word Augmentor

  #284 opened 3 years ago by rajat-tech-002
  1