Open
Description
How can the output of nltk be suppressed when loading sacrebleu via the evaluate library?
The minimal code is as follows:
import evaluate
bleu = evaluate.load("sacrebleu")
Then the output in the Jupyter Notebook is as follows:
Using the latest cached version of the module from /home/jupyter-raptor/.cache/huggingface/modules/evaluate_modules/metrics/evaluate-metric--sacrebleu/28676bf65b4f88b276df566e48e603732d0b4afd237603ebdf92acaacf5be99b (last modified on Fri Nov 8 20:44:01 2024) since it couldn't be found locally at evaluate-metric--sacrebleu, or remotely on the Hugging Face Hub.
[nltk_data] Downloading package wordnet to /home/jupyter-
[nltk_data] raptor/nltk_data...
[nltk_data] Package wordnet is already up-to-date!
[nltk_data] Downloading package punkt to /home/jupyter-
[nltk_data] raptor/nltk_data...
[nltk_data] Package punkt is already up-to-date!
[nltk_data] Downloading package omw-1.4 to /home/jupyter-
[nltk_data] raptor/nltk_data...
[nltk_data] Package omw-1.4 is already up-to-date!
This issue also happens for chrf, meteor and bertscore (and probably others).
Metadata
Metadata
Assignees
Labels
No labels