mixtral accuracy script is failing with nltk==3.9.1

[arjunsuresh]

cmuser@22852e086ad2:~/CM/repos/gateoverflow@mlperf-automations/script$ /home/cmuser/venv/cm/bin/python3 '/home/cmuser/CM/repos/local/cache/39a6f9adec6e40c0/inference/language/mixtral-8x7b/evaluate-accuracy.py' --checkpoint-path '/home/cmuser/CM/repos/local/cache/cab0c6b503c9423a/repo' --mlperf-accuracy-file '/home/cmuser/gh_action_results/test_results/gh_action-reference-cpu-pytorch-v2.5.1-default_config/mixtral-8x7b/offline/accuracy/mlperf_log_accuracy.json' --dataset-file '/home/cmuser/CM/repos/local/cache/8935e6cb4e364efd/mixtral-test-dataset.pkl' --dtype int32 > '/home/cmuser/gh_action_results/test_results/gh_action-reference-cpu-pytorch-v2.5.1-default_config/mixtral-8x7b/offline/accuracy/accuracy.txt'
[nltk_data] Downloading package punkt to /home/cmuser/nltk_data...
[nltk_data]   Package punkt is already up-to-date!
Traceback (most recent call last):
  File "/home/cmuser/CM/repos/local/cache/39a6f9adec6e40c0/inference/language/mixtral-8x7b/evaluate-accuracy.py", line 248, in <module>
    main()
  File "/home/cmuser/CM/repos/local/cache/39a6f9adec6e40c0/inference/language/mixtral-8x7b/evaluate-accuracy.py", line 190, in main
    preds, targets = postprocess_text(
  File "/home/cmuser/CM/repos/local/cache/39a6f9adec6e40c0/inference/language/mixtral-8x7b/evaluate-accuracy.py", line 97, in postprocess_text
    preds = ["\n".join(nltk.sent_tokenize(pred)) for pred in preds]
  File "/home/cmuser/CM/repos/local/cache/39a6f9adec6e40c0/inference/language/mixtral-8x7b/evaluate-accuracy.py", line 97, in <listcomp>
    preds = ["\n".join(nltk.sent_tokenize(pred)) for pred in preds]
  File "/home/cmuser/venv/cm/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 119, in sent_tokenize
    tokenizer = _get_punkt_tokenizer(language)
  File "/home/cmuser/venv/cm/lib/python3.10/site-packages/nltk/tokenize/__init__.py", line 105, in _get_punkt_tokenizer
    return PunktTokenizer(language)
  File "/home/cmuser/venv/cm/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1744, in __init__
    self.load_lang(lang)
  File "/home/cmuser/venv/cm/lib/python3.10/site-packages/nltk/tokenize/punkt.py", line 1749, in load_lang
    lang_dir = find(f"tokenizers/punkt_tab/{lang}/")
  File "/home/cmuser/venv/cm/lib/python3.10/site-packages/nltk/data.py", line 579, in find
    raise LookupError(resource_not_found)
LookupError:
**********************************************************************
  Resource punkt_tab not found.
  Please use the NLTK Downloader to obtain the resource:

  >>> import nltk
  >>> nltk.download('punkt_tab')

  For more information see: https://www.nltk.org/data.html

  Attempted to load tokenizers/punkt_tab/english/

  Searched in:
    - '/home/cmuser/nltk_data'
    - '/home/cmuser/venv/cm/nltk_data'
    - '/home/cmuser/venv/cm/share/nltk_data'
    - '/home/cmuser/venv/cm/lib/nltk_data'
    - '/usr/share/nltk_data'
    - '/usr/local/share/nltk_data'
    - '/usr/lib/nltk_data'
    - '/usr/local/lib/nltk_data'
**********************************************************************

It works fine for nltk==3.8.1.