public-mirrors/Kokoro-FastAPI
1
0
Fork 0
mirror of https://github.com/remsky/Kokoro-FastAPI.git synced 2025-04-13 09:39:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

changes to how money and numbers are handled

Browse source
This commit is contained in:
Fireblade 2025-02-15 17:48:12 -05:00
parent b00c9ec28d
commit 3290bada2e
2 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
api/src/services/text_processing/normalizer.py
View file

@ -136,10 +136,10 @@ def handle_money(m: re.Match[str]) -> str:
m = m.group() m = m.group()
bill = "dollar" if m[0] == "$" else "pound" bill = "dollar" if m[0] == "$" else "pound"
if m[-1].isalpha(): if m[-1].isalpha():
return f"{m[1:]} {bill}s" return f"{INFLECT_ENGINE.number_to_words(m[1:])} {bill}s"
elif "." not in m: elif "." not in m:
s = "" if m[1:] == "1" else "s" s = "" if m[1:] == "1" else "s"
return f"{m[1:]} {bill}{s}" return f"{INFLECT_ENGINE.number_to_words(m[1:])} {bill}{s}"
b, c = m[1:].split(".") b, c = m[1:].split(".")
s = "" if b == "1" else "s" s = "" if b == "1" else "s"
c = int(c.ljust(2, "0")) c = int(c.ljust(2, "0"))
@ -148,7 +148,7 @@ def handle_money(m: re.Match[str]) -> str:
if m[0] == "$" if m[0] == "$"
else ("penny" if c == 1 else "pence") else ("penny" if c == 1 else "pence")
) )
return f"{b} {bill}{s} and {c} {coins}" return f"{INFLECT_ENGINE.number_to_words(b)} {bill}{s} and {INFLECT_ENGINE.number_to_words(c)} {coins}"
def handle_decimal(num: re.Match[str]) -> str: def handle_decimal(num: re.Match[str]) -> str:
@ -259,17 +259,18 @@ def normalize_text(text: str,normalization_options: NormalizationOptions) -> str
text = re.sub(r"(?i)\b(y)eah?\b", r"\1e'a", text) text = re.sub(r"(?i)\b(y)eah?\b", r"\1e'a", text)
# Handle numbers and money # Handle numbers and money
text = re.sub(
r"\d*\.\d+|\b\d{4}s?\b|(?<!:)\b(?:[1-9]|1[0-2]):[0-5]\d\b(?!:)", split_num, text
)
text = re.sub(r"(?<=\d),(?=\d)", "", text) text = re.sub(r"(?<=\d),(?=\d)", "", text)
text = re.sub( text = re.sub(
r"(?i)[$£]\d+(?:\.\d+)?(?: hundred| thousand| (?:[bm]|tr)illion)*\b|[$£]\d+\.\d\d?\b", r"(?i)[$£]\d+(?:\.\d+)?(?: hundred| thousand| (?:[bm]|tr)illion)*\b|[$£]\d+\.\d\d?\b",
handle_money, handle_money,
text, text,
) )
text = re.sub(
r"\d*\.\d+|\b\d{4}s?\b|(?<!:)\b(?:[1-9]|1[0-2]):[0-5]\d\b(?!:)", split_num, text
)
text = re.sub(r"\d*\.\d+", handle_decimal, text) text = re.sub(r"\d*\.\d+", handle_decimal, text)
# Handle various formatting # Handle various formatting

2
api/tests/test_normalizer.py
View file

@ -88,4 +88,4 @@ def test_non_url_text():
"""Test that non-URL text is unaffected""" """Test that non-URL text is unaffected"""
assert normalize_text("This is not.a.url text",normalization_options=NormalizationOptions()) == "This is not-a-url text" assert normalize_text("This is not.a.url text",normalization_options=NormalizationOptions()) == "This is not-a-url text"
assert normalize_text("Hello, how are you today?",normalization_options=NormalizationOptions()) == "Hello, how are you today?" assert normalize_text("Hello, how are you today?",normalization_options=NormalizationOptions()) == "Hello, how are you today?"
assert normalize_text("It costs $50.",normalization_options=NormalizationOptions()) == "It costs 50 dollars." assert normalize_text("It costs $50.",normalization_options=NormalizationOptions()) == "It costs fifty dollars."