From 528f92f7a2a26cade1c57ccf26b0ba6524e7cae5 Mon Sep 17 00:00:00 2001
From: TnR2 <115166373+TnR2@users.noreply.github.com>
Date: 星期三, 01 十月 2025 14:45:17 +0800
Subject: [PATCH] fix: handle empty strings after event removal in transcription processing (def rich_transcription_postprocess(s)) (#2681)
---
fun_text_processing/inverse_text_normalization/ru/verbalizers/cardinal.py | 16 +++++++++++-----
1 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/fun_text_processing/inverse_text_normalization/ru/verbalizers/cardinal.py b/fun_text_processing/inverse_text_normalization/ru/verbalizers/cardinal.py
index ab5afee..d83043e 100644
--- a/fun_text_processing/inverse_text_normalization/ru/verbalizers/cardinal.py
+++ b/fun_text_processing/inverse_text_normalization/ru/verbalizers/cardinal.py
@@ -1,6 +1,9 @@
-
import pynini
-from fun_text_processing.text_normalization.en.graph_utils import DAMO_NOT_QUOTE, GraphFst, delete_space
+from fun_text_processing.text_normalization.en.graph_utils import (
+ DAMO_NOT_QUOTE,
+ GraphFst,
+ delete_space,
+)
from pynini.lib import pynutil
@@ -20,16 +23,19 @@
optional_sign = pynini.closure(
pynutil.delete("negative:")
+ delete_space
- + pynutil.delete("\"")
+ + pynutil.delete('"')
+ DAMO_NOT_QUOTE
- + pynutil.delete("\"")
+ + pynutil.delete('"')
+ delete_space,
0,
1,
)
graph = (
- optional_sign + pynutil.delete("integer: \"") + pynini.closure(DAMO_NOT_QUOTE, 1) + pynutil.delete("\"")
+ optional_sign
+ + pynutil.delete('integer: "')
+ + pynini.closure(DAMO_NOT_QUOTE, 1)
+ + pynutil.delete('"')
)
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
--
Gitblit v1.9.1