oliverguhr / fullstop-deep-punctuation-prediction

A model that predicts the punctuation of English, Italian, French and German texts.
https://huggingface.co/oliverguhr/fullstop-punctuation-multilang-large
MIT License
70 stars 13 forks source link

Error when training new language #16

Closed RizkiNoor16 closed 1 year ago

RizkiNoor16 commented 1 year ago

I am still a beginner in language modeling, and I have tried to follow the step-by-step training process for other languages. However, I encountered an error as shown below. Could you please help me on how to resolve this error?

""" invoking test run for model: xlm-roberta-large-id-1-task2 loading data from pickle data/sepp_nlg_2021_train_dev_data_v5.zip_dev_id_2.pickle loading data from pickle data/sepp_nlg_2021_train_dev_data_v5.zip_train_id_2.pickle tokenize training data 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:08<00:00, 8.45s/it] tokenize validation data 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.90s/it] Unexpected error: <class 'KeyError'> """