Fix Japanese TN word spans with quoted spaces

nemo_text_processing/text_normalization/ja/taggers/word.py

@@ -15,7 +15,7 @@
 
 from pynini.lib import pynutil
 
-from nemo_text_processing.text_normalization.ja.graph_utils import NEMO_NOT_SPACE, GraphFst
+from nemo_text_processing.text_normalization.ja.graph_utils import NEMO_NOT_QUOTE, GraphFst
 
 
 class WordFst(GraphFst):
@@ -26,5 +26,5 @@ class WordFst(GraphFst):
 
     def __init__(self, deterministic: bool = True):
         super().__init__(name="word", kind="classify", deterministic=deterministic)
-        word = pynutil.insert("name: \"") + NEMO_NOT_SPACE + pynutil.insert("\"")
-        self.fst = word.optimize()
+        word = pynutil.insert("name: \"") + NEMO_NOT_QUOTE + pynutil.insert("\"")
+        self.fst = word.optimize()

tests/nemo_text_processing/ja/data_text_normalization/test_cases_word.txt

@@ -0,0 +1 @@
+彼は“Hello World”というプログラムを実行した。~彼は“Hello World”というプログラムを実行した。

tests/nemo_text_processing/ja/test_word.py

@@ -0,0 +1,32 @@
+# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import pytest
+from parameterized import parameterized
+
+from nemo_text_processing.text_normalization.normalize import Normalizer
+
+from ..utils import CACHE_DIR, parse_test_case_file
+
+
+class TestWord:
+    normalizer_ja = Normalizer(lang='ja', cache_dir=CACHE_DIR, overwrite_cache=False, input_case='cased')
+
+    @parameterized.expand(parse_test_case_file('ja/data_text_normalization/test_cases_word.txt'))
+    @pytest.mark.run_only_on('CPU')
+    @pytest.mark.unit
+    def test_norm_word(self, test_input, expected):
+        preds = self.normalizer_ja.normalize(test_input)
+        assert expected == preds