IndoNLP / nusa-writes

NusaWrites is an in-depth analysis of corpora collection strategy and a comprehensive language modeling benchmark for underrepresented and extremely low-resource Indonesian local languages.
Apache License 2.0
24 stars 2 forks source link

Both `load_benchmark('NusaTranslation')` and `load_benchmark('NusaWrites')` tries to download a file that does not exist #19

Closed ShandyDrm closed 11 months ago

ShandyDrm commented 11 months ago

Python 3.10, NusaCrowd 0.1.2

Error message:
FileNotFoundError: Couldn't find file at https://raw.githubusercontent.com/IndoNLP/nusa-writes/main/data/nusa_kalimat-mt-bug-train.csv

Screenshot 2023-12-15 at 20 34 56 copy
SamuelCahyawijaya commented 11 months ago

Hi @ShandyDrm , thanks for reporting.

We have fixed the problem and you can try installing the new version nusacrowd==0.1.3

Please let us know if you find any further problems.