From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
fun_text_processing/inverse_text_normalization/export_models.py | 137 +++++++++++++++++++++++++++++++--------------
1 files changed, 95 insertions(+), 42 deletions(-)
diff --git a/fun_text_processing/inverse_text_normalization/export_models.py b/fun_text_processing/inverse_text_normalization/export_models.py
index 9460ad9..0597f7f 100644
--- a/fun_text_processing/inverse_text_normalization/export_models.py
+++ b/fun_text_processing/inverse_text_normalization/export_models.py
@@ -3,11 +3,16 @@
from argparse import ArgumentParser
from fun_text_processing.text_normalization.en.graph_utils import generator_main
+
def parse_args():
parser = ArgumentParser()
-
+
parser.add_argument(
- "--language", help="language", choices=['de', 'en', 'es', 'fr', 'id', 'ja', 'ko', 'pt', 'ru', 'vi', 'zh'], default="en", type=str
+ "--language",
+ help="language",
+ choices=["de", "en", "es", "fr", "id", "ja", "ko", "pt", "ru", "vi", "zh"],
+ default="en",
+ type=str,
)
parser.add_argument(
"--export_dir",
@@ -17,46 +22,95 @@
)
return parser.parse_args()
-def get_grammars(lang: str='en'):
- if lang=='de':
- from fun_text_processing.inverse_text_normalization.de.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.de.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='en':
- from fun_text_processing.inverse_text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='es':
- from fun_text_processing.inverse_text_normalization.es.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.es.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='fr':
- from fun_text_processing.inverse_text_normalization.fr.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.fr.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='id':
- from fun_text_processing.inverse_text_normalization.id.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.id.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='ja':
- from fun_text_processing.inverse_text_normalization.ja.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.ja.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='ko':
- from fun_text_processing.inverse_text_normalization.ko.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.ko.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='pt':
- from fun_text_processing.inverse_text_normalization.pt.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.pt.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='ru':
- from fun_text_processing.inverse_text_normalization.ru.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.ru.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='vi':
- from fun_text_processing.inverse_text_normalization.vi.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.vi.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='zh':
- from fun_text_processing.inverse_text_normalization.zh.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.zh.verbalizers.verbalize_final import VerbalizeFinalFst
- else:
- from fun_text_processing.inverse_text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.inverse_text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
+def get_grammars(lang: str = "en"):
+ if lang == "de":
+ from fun_text_processing.inverse_text_normalization.de.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.de.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "en":
+ from fun_text_processing.inverse_text_normalization.en.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.en.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "es":
+ from fun_text_processing.inverse_text_normalization.es.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.es.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "fr":
+ from fun_text_processing.inverse_text_normalization.fr.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.fr.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "id":
+ from fun_text_processing.inverse_text_normalization.id.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.id.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "ja":
+ from fun_text_processing.inverse_text_normalization.ja.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.ja.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "ko":
+ from fun_text_processing.inverse_text_normalization.ko.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.ko.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "pt":
+ from fun_text_processing.inverse_text_normalization.pt.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.pt.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "ru":
+ from fun_text_processing.inverse_text_normalization.ru.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.ru.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "vi":
+ from fun_text_processing.inverse_text_normalization.vi.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.vi.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "zh":
+ from fun_text_processing.inverse_text_normalization.zh.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.zh.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ else:
+ from fun_text_processing.inverse_text_normalization.en.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.inverse_text_normalization.en.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
- return ClassifyFst().fst, VerbalizeFinalFst().fst
+ return ClassifyFst().fst, VerbalizeFinalFst().fst
+
if __name__ == "__main__":
args = parse_args()
@@ -70,5 +124,4 @@
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})
- print(f'Time to generate graph: {round(perf_counter() - start_time, 2)} sec')
-
+ print(f"Time to generate graph: {round(perf_counter() - start_time, 2)} sec")
--
Gitblit v1.9.1