From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
fun_text_processing/inverse_text_normalization/zh/verbalizers/money.py | 11 +++++++----
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/fun_text_processing/inverse_text_normalization/zh/verbalizers/money.py b/fun_text_processing/inverse_text_normalization/zh/verbalizers/money.py
index 5aaac24..74fedde 100755
--- a/fun_text_processing/inverse_text_normalization/zh/verbalizers/money.py
+++ b/fun_text_processing/inverse_text_normalization/zh/verbalizers/money.py
@@ -1,6 +1,9 @@
-
import pynini
-from fun_text_processing.inverse_text_normalization.zh.graph_utils import DAMO_CHAR, GraphFst, delete_space
+from fun_text_processing.inverse_text_normalization.zh.graph_utils import (
+ DAMO_CHAR,
+ GraphFst,
+ delete_space,
+)
from pynini.lib import pynutil
@@ -18,9 +21,9 @@
unit = (
pynutil.delete("currency:")
+ delete_space
- + pynutil.delete("\"")
+ + pynutil.delete('"')
+ pynini.closure(DAMO_CHAR - " ", 1)
- + pynutil.delete("\"")
+ + pynutil.delete('"')
)
graph = unit + delete_space + decimal.numbers
delete_tokens = self.delete_tokens(graph)
--
Gitblit v1.9.1