diff --git a/pinecone_text/sparse/bm25_tokenizer.py b/pinecone_text/sparse/bm25_tokenizer.py
index 9513176..bbdf23c 100644
--- a/pinecone_text/sparse/bm25_tokenizer.py
+++ b/pinecone_text/sparse/bm25_tokenizer.py
@@ -44,7 +44,7 @@ def nltk_setup() -> None:
             nltk.download("stopwords")
 
     def __call__(self, text: str) -> List[str]:
-        tokens = word_tokenize(text)
+        tokens = word_tokenize(text, self.language)
         if self.lower_case:
             tokens = [word.lower() for word in tokens]
         if self.remove_punctuation: