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/fr/verbalizers/ordinal.py | 21 ++++++++++++---------
1 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/fun_text_processing/inverse_text_normalization/fr/verbalizers/ordinal.py b/fun_text_processing/inverse_text_normalization/fr/verbalizers/ordinal.py
index 92d715b..aa46237 100644
--- a/fun_text_processing/inverse_text_normalization/fr/verbalizers/ordinal.py
+++ b/fun_text_processing/inverse_text_normalization/fr/verbalizers/ordinal.py
@@ -1,4 +1,3 @@
-
import pynini
from fun_text_processing.inverse_text_normalization.fr.graph_utils import (
DAMO_DIGIT,
@@ -26,9 +25,9 @@
graph_integer = (
pynutil.delete("integer:")
+ delete_space
- + pynutil.delete("\"")
+ + pynutil.delete('"')
+ pynini.closure(DAMO_NOT_QUOTE, 1)
- + pynutil.delete("\"")
+ + pynutil.delete('"')
)
replace_suffix = pynini.union(
@@ -37,22 +36,26 @@
pynini.cross("r", "食"),
pynini.cross("s", "刷"),
)
- replace_suffix = pynutil.delete(" morphosyntactic_features: \"") + replace_suffix.plus
+ replace_suffix = pynutil.delete(' morphosyntactic_features: "') + replace_suffix.plus
graph_arabic = graph_integer + replace_suffix.plus
# For roman.
- graph_roman_digits = pynini.string_file(get_abs_path("data/roman/digits_large.tsv")).invert()
+ graph_roman_digits = pynini.string_file(
+ get_abs_path("data/roman/digits_large.tsv")
+ ).invert()
graph_roman_ties = pynini.string_file(get_abs_path("data/roman/ties_large.tsv")).invert()
- graph_roman_hundreds = pynini.string_file(get_abs_path("data/roman/hundreds_large.tsv")).invert()
+ graph_roman_hundreds = pynini.string_file(
+ get_abs_path("data/roman/hundreds_large.tsv")
+ ).invert()
graph_roman_zero_digit = pynutil.delete("0")
- graph_roman_hundreds = DAMO_DIGIT ** 3 @ (
+ graph_roman_hundreds = DAMO_DIGIT**3 @ (
graph_roman_hundreds
+ pynini.union(graph_roman_ties, graph_roman_zero_digit)
+ pynini.union(graph_roman_digits, graph_roman_zero_digit)
)
- graph_roman_ties = DAMO_DIGIT ** 2 @ (
+ graph_roman_ties = DAMO_DIGIT**2 @ (
graph_roman_ties + pynini.union(graph_roman_digits, graph_roman_zero_digit)
)
graph_roman_digits = DAMO_DIGIT @ graph_roman_digits
@@ -62,7 +65,7 @@
graph_roman = (graph_integer @ graph_roman_integers) + replace_suffix
graph_roman += pynini.cross("/", " ") + "si猫cle"
- graph = (graph_roman | graph_arabic) + pynutil.delete("\"")
+ graph = (graph_roman | graph_arabic) + pynutil.delete('"')
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
--
Gitblit v1.9.1