Skip to content

Commit fa304a2

Browse files
committed
First draft of Korean Cardinal ITN
Sparrowhawk testing is not done yet. Signed-off-by: hmlee245 <hmlee245@gmail.com>
1 parent 3e4ac3e commit fa304a2

File tree

25 files changed

+1287
-2
lines changed

25 files changed

+1287
-2
lines changed

nemo_text_processing/inverse_text_normalization/inverse_normalize.py

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -131,6 +131,11 @@ def __init__(
131131
from nemo_text_processing.inverse_text_normalization.ja.verbalizers.verbalize_final import (
132132
VerbalizeFinalFst,
133133
)
134+
elif lang == 'ko': # Korean
135+
from nemo_text_processing.inverse_text_normalization.ko.taggers.tokenize_and_classify import ClassifyFst
136+
from nemo_text_processing.inverse_text_normalization.ko.verbalizers.verbalize_final import (
137+
VerbalizeFinalFst,
138+
)
134139

135140
self.tagger = ClassifyFst(
136141
cache_dir=cache_dir, whitelist=whitelist, overwrite_cache=overwrite_cache, input_case=input_case
@@ -175,7 +180,7 @@ def parse_args():
175180
parser.add_argument(
176181
"--language",
177182
help="language",
178-
choices=['en', 'de', 'es', 'pt', 'ru', 'fr', 'sv', 'vi', 'ar', 'es_en', 'zh', 'hi', 'hy', 'mr', 'ja'],
183+
choices=['en', 'de', 'es', 'pt', 'ru', 'fr', 'sv', 'vi', 'ar', 'es_en', 'zh', 'hi', 'hy', 'mr', 'ja','ko'],
179184
default="en",
180185
type=str,
181186
)
Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,17 @@
1+
# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
from nemo_text_processing.inverse_text_normalization.ko.taggers.tokenize_and_classify import ClassifyFst
16+
from nemo_text_processing.inverse_text_normalization.ko.verbalizers.verbalize import VerbalizeFst
17+
from nemo_text_processing.inverse_text_normalization.ko.verbalizers.verbalize_final import VerbalizeFinalFst

0 commit comments

Comments
 (0)