From 3df109adfccedeb134dea4ba2ea9a2da89872048 Mon Sep 17 00:00:00 2001
From: Isuxiz Slidder <48672727+Isuxiz@users.noreply.github.com>
Date: 星期一, 31 三月 2025 17:51:52 +0800
Subject: [PATCH] Update model.py to fix "IndexError: index 1 is out of bounds for dimension 1 with size 0" (#2454)
---
fun_text_processing/text_normalization/export_models.py | 84 +++++++++++++++++++++++++++++------------
1 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/fun_text_processing/text_normalization/export_models.py b/fun_text_processing/text_normalization/export_models.py
index 72c3ff8..09fab45 100644
--- a/fun_text_processing/text_normalization/export_models.py
+++ b/fun_text_processing/text_normalization/export_models.py
@@ -3,14 +3,23 @@
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', 'ru', 'zh'], default="en", type=str
+ "--language",
+ help="language",
+ choices=["de", "en", "es", "ru", "zh"],
+ default="en",
+ type=str,
)
parser.add_argument(
- "--input_case", help="input capitalization", choices=["lower_cased", "cased"], default="cased", type=str
+ "--input_case",
+ help="input capitalization",
+ choices=["lower_cased", "cased"],
+ default="cased",
+ type=str,
)
parser.add_argument(
"--export_dir",
@@ -20,27 +29,53 @@
)
return parser.parse_args()
-def get_grammars(lang: str="en", input_case: str="cased"):
- if lang=='de':
- from fun_text_processing.text_normalization.de.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.de.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='en':
- from fun_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='es':
- from fun_text_processing.text_normalization.es.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.es.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='ru':
- from fun_text_processing.text_normalization.ru.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.ru.verbalizers.verbalize_final import VerbalizeFinalFst
- elif lang=='zh':
- from fun_text_processing.text_normalization.zh.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.zh.verbalizers.verbalize_final import VerbalizeFinalFst
- else:
- from fun_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
- from fun_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
- return ClassifyFst(input_case=input_case).fst, VerbalizeFinalFst().fst
+def get_grammars(lang: str = "en", input_case: str = "cased"):
+ if lang == "de":
+ from fun_text_processing.text_normalization.de.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.de.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "en":
+ from fun_text_processing.text_normalization.en.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.en.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "es":
+ from fun_text_processing.text_normalization.es.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.es.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "ru":
+ from fun_text_processing.text_normalization.ru.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.ru.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ elif lang == "zh":
+ from fun_text_processing.text_normalization.zh.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.zh.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+ else:
+ from fun_text_processing.text_normalization.en.taggers.tokenize_and_classify import (
+ ClassifyFst,
+ )
+ from fun_text_processing.text_normalization.en.verbalizers.verbalize_final import (
+ VerbalizeFinalFst,
+ )
+
+ return ClassifyFst(input_case=input_case).fst, VerbalizeFinalFst().fst
+
if __name__ == "__main__":
args = parse_args()
@@ -54,5 +89,4 @@
tagger_fst, verbalizer_fst = get_grammars(args.language, args.input_case)
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