From 6b7134d49167d4410b18a10eebd92d163d83828c Mon Sep 17 00:00:00 2001
From: nichongjia-2007 <nichongjia@gmail.com>
Date: 星期三, 04 一月 2023 16:49:51 +0800
Subject: [PATCH] modify export_models.py
---
fun_text_processing/inverse_text_normalization/export_models.py | 17 +++++++++++++++--
fun_text_processing/version.txt | 2 +-
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/fun_text_processing/inverse_text_normalization/export_models.py b/fun_text_processing/inverse_text_normalization/export_models.py
index 7618f49..be6394f 100644
--- a/fun_text_processing/inverse_text_normalization/export_models.py
+++ b/fun_text_processing/inverse_text_normalization/export_models.py
@@ -21,6 +21,12 @@
parser.add_argument(
"--language", help="language", choices=['de', 'en', 'es', 'fr', 'id', 'ja', 'ko', 'pt', 'ru', 'vi', 'zh'], default="en", type=str
)
+
+ parser.add_argument(
+ "--token_and_classify_and_verbalize", help="export the single token&classify and verbalize or combined", choices=['single', 'combine'],
+ default="single", type=str
+ )
+
parser.add_argument(
"--export_dir",
help="path to export directory. Default to current directory.",
@@ -77,10 +83,17 @@
os.makedirs(export_dir, exist_ok=True)
tagger_far_file = os.path.join(export_dir, args.language + "_itn_tagger.far")
verbalizer_far_file = os.path.join(export_dir, args.language + "_itn_verbalizer.far")
+ tager_and_verbalizer_far_file = os.path.join(export_dir, args.language, "model.far" )
start_time = perf_counter()
tagger_fst, verbalizer_fst = get_grammars(args.language)
- generator_main(tagger_far_file, {"tokenize_and_classify": tagger_fst})
- generator_main(verbalizer_far_file, {"verbalize": verbalizer_fst})
+
+ if args.token_and_classify_and_verbalize == 'single':
+ generator_main(tagger_far_file, {"tokenize_and_classify": tagger_fst})
+ generator_main(verbalizer_far_file, {"verbalize": verbalizer_fst})
+ elif args.token_and_classify_and_verbalize == 'combine':
+ if not os.path.exists(os.path.join(export_dir, args.language)):
+ os.makedirs(os.path.join(export_dir, args.language))
+ generator_main(tager_and_verbalizer_far_file, {"tokenize_and_classify": tagger_fst, "verbalize": verbalizer_fst})
print(f'Time to generate graph: {round(perf_counter() - start_time, 2)} sec')
diff --git a/fun_text_processing/version.txt b/fun_text_processing/version.txt
index 6e8bf73..17e51c3 100644
--- a/fun_text_processing/version.txt
+++ b/fun_text_processing/version.txt
@@ -1 +1 @@
-0.1.0
+0.1.1
--
Gitblit v1.9.1