From b7312e9f0b48fa5dab09cd8bede5eba302313664 Mon Sep 17 00:00:00 2001
From: HuangLiangJie <mailoflawrence@gmail.com>
Date: Wed, 9 Nov 2022 14:45:02 +0800
Subject: [PATCH] Revised TN qualifier for measure notation, test=tts (#2629)

---
 .../other/tn/data/textnorm_test_cases.txt     |  4 ++-
 .../frontend/zh_normalization/quantifier.py   | 26 +++++++++++++++++++
 .../zh_normalization/text_normlization.py     |  2 ++
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/examples/other/tn/data/textnorm_test_cases.txt b/examples/other/tn/data/textnorm_test_cases.txt
index e9a479b4..17e90d0b 100644
--- a/examples/other/tn/data/textnorm_test_cases.txt
+++ b/examples/other/tn/data/textnorm_test_cases.txt
@@ -122,4 +122,6 @@ iPad Pro的秒控键盘这次也推出白色版本。|iPad Pro的秒控键盘这
 近期也一反常态地发表看空言论|近期也一反常态地发表看空言论
 985|九八五
 12~23|十二到二十三
-12-23|十二到二十三
\ No newline at end of file
+12-23|十二到二十三
+25cm²|二十五平方厘米
+25m|米
\ No newline at end of file
diff --git a/paddlespeech/t2s/frontend/zh_normalization/quantifier.py b/paddlespeech/t2s/frontend/zh_normalization/quantifier.py
index 268d7229..598030e4 100644
--- a/paddlespeech/t2s/frontend/zh_normalization/quantifier.py
+++ b/paddlespeech/t2s/frontend/zh_normalization/quantifier.py
@@ -18,6 +18,25 @@ from .num import num2str
 # 温度表达式，温度会影响负号的读法
 # -3°C 零下三度
 RE_TEMPERATURE = re.compile(r'(-?)(\d+(\.\d+)?)(°C|℃|度|摄氏度)')
+measure_dict = {
+    "cm2": "平方厘米",
+    "cm²": "平方厘米",
+    "cm3": "立方厘米",
+    "cm³": "立方厘米",
+    "cm": "厘米",
+    "db": "分贝",
+    "ds": "毫秒",
+    "kg": "千克",
+    "km": "千米",
+    "m2": "平方米",
+    "m²": "平方米",
+    "m³": "立方米",
+    "m3": "立方米",
+    "ml": "毫升",
+    "m": "米",
+    "mm": "毫米",
+    "s": "秒"
+}
 
 
 def replace_temperature(match) -> str:
@@ -35,3 +54,10 @@ def replace_temperature(match) -> str:
     unit: str = "摄氏度" if unit == "摄氏度" else "度"
     result = f"{sign}{temperature}{unit}"
     return result
+
+
+def replace_measure(sentence) -> str:
+    for q_notation in measure_dict:
+        if q_notation in sentence:
+            sentence = sentence.replace(q_notation, measure_dict[q_notation])
+    return sentence
diff --git a/paddlespeech/t2s/frontend/zh_normalization/text_normlization.py b/paddlespeech/t2s/frontend/zh_normalization/text_normlization.py
index bc663c70..8f8e3b07 100644
--- a/paddlespeech/t2s/frontend/zh_normalization/text_normlization.py
+++ b/paddlespeech/t2s/frontend/zh_normalization/text_normlization.py
@@ -46,6 +46,7 @@ from .phonecode import RE_TELEPHONE
 from .phonecode import replace_mobile
 from .phonecode import replace_phone
 from .quantifier import RE_TEMPERATURE
+from .quantifier import replace_measure
 from .quantifier import replace_temperature
 
 
@@ -91,6 +92,7 @@ class TextNormalizer():
         sentence = RE_TIME.sub(replace_time, sentence)
 
         sentence = RE_TEMPERATURE.sub(replace_temperature, sentence)
+        sentence = replace_measure(sentence)
         sentence = RE_FRAC.sub(replace_frac, sentence)
         sentence = RE_PERCENTAGE.sub(replace_percentage, sentence)
         sentence = RE_MOBILE_PHONE.sub(replace_mobile, sentence)
-- 
GitLab