nltk

Signed-off-by: peter szemraj <[email protected]>

app.py

@@ -34,9 +34,12 @@ from utils import load_example_filenames, saves_summary, truncate_word_count
 
 _here = Path(__file__).parent
 
-os.environ["NLTK_DATA"] = str(_here / "nltk_data")
-nltk.download("punkt", force=True, download_dir=os.environ["NLTK_DATA"], quiet=True)
-nltk.download("popular", force=True, download_dir=os.environ["NLTK_DATA"])
+# os.environ["NLTK_DATA"] = str(_here / "nltk_data")
+nltk.download("punkt", force=True, quiet=True)
+nltk.download(
+    "popular",
+    force=True,
+)
 
 
 MODEL_OPTIONS = [

utils.py

@@ -4,17 +4,24 @@
 
 import re
 import subprocess
+from collections import defaultdict
 from datetime import datetime
+from itertools import combinations
 from pathlib import Path
+from typing import List
 
+import nltk
 import torch
 from natsort import natsorted
-from typing import List
+from nltk.corpus import stopwords
 from nltk.tokenize import sent_tokenize, word_tokenize
-from itertools import combinations
-from collections import defaultdict
 from rapidfuzz import fuzz
-from nltk.corpus import stopwords
+
+nltk.download("punkt", quiet=True)
+nltk.download(
+    "popular",
+    quiet=True,
+)
 
 
 def validate_pytorch2(torch_version: str = None):