Add DeprecationWarning to ser.str.subword_tokenize (#8603)

This PR adds deprecationWarning to `ser.str.subword_tokenize` .

Checkout related issue for details:  #8604

Authors:
  - Vibhu Jawa (https://github.com/VibhuJawa)

Approvers:
  - GALI PREM SAGAR (https://github.com/galipremsagar)

URL: #8603

python/cudf/cudf/core/column/string.py

@@ -4620,6 +4620,9 @@ def subword_tokenize(
         This function requires about 21x the number of character bytes
         in the input strings column as working memory.
 
+        ``ser.str.subword_tokenize`` will be depreciated in future versions.
+        Use ``cudf.core.subword_tokenizer.SubwordTokenizer`` instead.
+
         Parameters
         ----------
         hash_file : str
@@ -4691,6 +4694,14 @@ def subword_tokenize(
         array([[0, 0, 2],
                [1, 0, 1]], dtype=uint32)
         """
+        warning_message = (
+            "`ser.str.subword_tokenize` API will be depreciated"
+            " in future versions of cudf.\n"
+            "Use `cudf.core.subword_tokenizer.SubwordTokenizer` "
+            "instead"
+        )
+
+        warnings.warn(warning_message, FutureWarning)
         tokens, masks, metadata = cpp_subword_tokenize_vocab_file(
             self._column,
             hash_file,