zenn
7101fdcd65
FastAPI backend, web UI, CosyVoice3/F5-TTS setup scripts, and handoff docs for GPU PC continuation. Co-authored-by: Cursor <cursoragent@cursor.com>
96 lines
2.6 KiB
Python
96 lines
2.6 KiB
Python
"""한국어 TTS용 간단한 텍스트 정규화."""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
|
|
_RE_MULTI_SPACE = re.compile(r"\s+")
|
|
_RE_EMAIL = re.compile(r"[\w.+-]+@[\w.-]+\.\w+")
|
|
_RE_URL = re.compile(r"https?://\S+")
|
|
|
|
|
|
def _digits_to_korean(num_str: str) -> str:
|
|
"""정수 문자열을 한글 읽기로 변환 (간단 버전)."""
|
|
if not num_str.isdigit():
|
|
return num_str
|
|
n = int(num_str.replace(",", ""))
|
|
if n == 0:
|
|
return "영"
|
|
units = ["", "만", "억", "조"]
|
|
small = ["", "일", "이", "삼", "사", "오", "육", "칠", "팔", "구"]
|
|
ten = ["", "십", "백", "천"]
|
|
|
|
def chunk_to_korean(x: int) -> str:
|
|
if x == 0:
|
|
return ""
|
|
parts: list[str] = []
|
|
s = f"{x:04d}"
|
|
for i, d in enumerate(s):
|
|
di = int(d)
|
|
if di == 0:
|
|
continue
|
|
if i == 0 and di == 1 and len(s) > 1:
|
|
parts.append(ten[3 - i])
|
|
elif di == 1 and i > 0:
|
|
parts.append(ten[3 - i])
|
|
else:
|
|
parts.append(small[di] + ten[3 - i])
|
|
return "".join(parts)
|
|
|
|
if n < 10000:
|
|
return chunk_to_korean(n)
|
|
|
|
result: list[str] = []
|
|
u = 0
|
|
while n > 0 and u < len(units):
|
|
part = n % 10000
|
|
n //= 10000
|
|
if part:
|
|
result.append(chunk_to_korean(part) + units[u])
|
|
u += 1
|
|
return "".join(reversed(result)) or num_str
|
|
|
|
|
|
def _replace_numbers(text: str) -> str:
|
|
def repl(m: re.Match[str]) -> str:
|
|
raw = m.group(0).replace(",", "")
|
|
return _digits_to_korean(raw)
|
|
|
|
return re.sub(r"\d[\d,]*", repl, text)
|
|
|
|
|
|
def preprocess_korean(text: str) -> str:
|
|
t = text.strip()
|
|
t = _RE_URL.sub(" 링크 ", t)
|
|
t = _RE_EMAIL.sub(" 이메일 ", t)
|
|
t = t.replace("&", " 앤드 ")
|
|
t = t.replace("%", " 퍼센트 ")
|
|
t = _replace_numbers(t)
|
|
t = _RE_MULTI_SPACE.sub(" ", t)
|
|
return t.strip()
|
|
|
|
|
|
def split_sentences(text: str, max_chars: int = 120) -> list[str]:
|
|
"""긴 텍스트를 문장 단위로 분리."""
|
|
parts = re.split(r"(?<=[.!?…])\s+|\n+", preprocess_korean(text))
|
|
chunks: list[str] = []
|
|
buf = ""
|
|
for p in parts:
|
|
p = p.strip()
|
|
if not p:
|
|
continue
|
|
if len(buf) + len(p) + 1 <= max_chars:
|
|
buf = f"{buf} {p}".strip() if buf else p
|
|
else:
|
|
if buf:
|
|
chunks.append(buf)
|
|
if len(p) <= max_chars:
|
|
buf = p
|
|
else:
|
|
for i in range(0, len(p), max_chars):
|
|
chunks.append(p[i : i + max_chars])
|
|
buf = ""
|
|
if buf:
|
|
chunks.append(buf)
|
|
return chunks or [text]
|