fix(voice): spell Korean numbers out before MeloTTS reads them
MeloTTS's Korean front end read "60%" digit by digit ("육영퍼센트") when
the Windows MeCab build did not tag what followed as a bound noun, and its
sentence splitter broke "4.2미터" at the dot ("사. 이미터"). The KR child
now spells decimals with 점, drops thousands commas and gives every other
whole number its Sino-Korean reading, leaving numbers before native
counters (시, 개, 마리, ...) to MeloTTS's own counter rule.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -24,12 +24,23 @@ import argparse
|
||||
import importlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import struct
|
||||
import sys
|
||||
import types
|
||||
|
||||
MODEL_SPEED_MAX = 1.25
|
||||
|
||||
# MeloTTS's Korean front end (g2pkk) reads a number with native numerals only before these counters,
|
||||
# and only when MeCab tags the counter. Any other number is spelled out only when MeCab tags what follows
|
||||
# as a bound noun, which differs between MeCab builds (on Windows "60%" was read "육영퍼센트"); the rest
|
||||
# goes digit by digit. Its sentence splitter also breaks at every dot and comma ("4.2" as "사. 이").
|
||||
# Same list as g2pkk's BOUND_NOUNS: numbers before them are left for its counter rule.
|
||||
NATIVE_COUNTERS = tuple("군데 권 개 그루 닢 대 두 마리 모 모금 뭇 발 발짝 방 번 벌 보루 살 수 술 시 쌈 움큼 "
|
||||
"정 짝 채 척 첩 축 켤레 톨 통".split())
|
||||
_DIGITS = "영일이삼사오육칠팔구"
|
||||
_NUMBER = re.compile(r"(?<![\d.,])(\d{1,3}(?:,\d{3})+|\d+)(?:\.(\d+))?(?![\d,]\d)(?!\.\d)([가-힣]*)")
|
||||
|
||||
|
||||
def split_speed(speed: float) -> tuple[float, float]:
|
||||
"""(the model's speed, the stretch factor after it); their product is ``speed``."""
|
||||
@@ -65,6 +76,39 @@ def stretch(audio, factor: float, rate: int, frame_ms: float = 30.0, search_ms:
|
||||
return y[:n_out]
|
||||
|
||||
|
||||
def sino_korean(num: str) -> str:
|
||||
"""Sino-Korean reading of a whole number: 1234 is 천이백삼십사, 10000 is 만, 100000000 is 일억."""
|
||||
n = int(num)
|
||||
if n == 0:
|
||||
return "영"
|
||||
out = ""
|
||||
for power, big in reversed(list(enumerate(("", "만", "억", "조", "경")))):
|
||||
group = n // 10 ** (4 * power) % 10000
|
||||
if not group:
|
||||
continue
|
||||
part = ""
|
||||
for digit, unit in zip(f"{group:04d}", ("천", "백", "십", "")):
|
||||
d = int(digit)
|
||||
if d:
|
||||
part += ("" if d == 1 and unit else _DIGITS[d]) + unit
|
||||
out += ("" if part == "일" and big == "만" else part) + big
|
||||
return out
|
||||
|
||||
|
||||
def spell_numbers_kr(text: str) -> str:
|
||||
"""Spell out the numbers MeloTTS would misread: decimals ("4.2" is 사점이) and every whole number
|
||||
not followed by a native counter (those are left for MeloTTS, which reads "3시" as 세시)."""
|
||||
def spell(m: re.Match) -> str:
|
||||
whole, frac, after = m.group(1), m.group(2), m.group(3)
|
||||
if frac is None and after.startswith(NATIVE_COUNTERS):
|
||||
return m.group(0)
|
||||
spoken = sino_korean(whole.replace(",", ""))
|
||||
if frac is not None:
|
||||
spoken += "점" + "".join(_DIGITS[int(d)] for d in frac)
|
||||
return spoken + after
|
||||
return _NUMBER.sub(spell, text)
|
||||
|
||||
|
||||
def korean_only_patches() -> None:
|
||||
"""MeloTTS imports its Japanese front end (module-level MeCab.Tagger()) even for Korean, and on
|
||||
Windows g2pkk asks for ``eunjeon`` instead of python-mecab-ko. Same fix as the M0 kit."""
|
||||
@@ -132,7 +176,10 @@ def main() -> int:
|
||||
req = json.loads(line)
|
||||
rate = int(req["rate"])
|
||||
model_speed, factor = split_speed(float(req.get("speed", args.speed)))
|
||||
audio = model.tts_to_file(str(req["text"]), speaker, None, speed=model_speed, quiet=True)
|
||||
text = str(req["text"])
|
||||
if args.language == "KR":
|
||||
text = spell_numbers_kr(text)
|
||||
audio = model.tts_to_file(text, speaker, None, speed=model_speed, quiet=True)
|
||||
audio = stretch(audio, factor, native)
|
||||
if rate != native:
|
||||
from math import gcd
|
||||
|
||||
@@ -192,6 +192,14 @@ is ready. Requests are served first come, first served by one TTS engine. `tts_c
|
||||
request's unsent sentences, and `tts_done` follows with `cancelled: true`. A sentence that fails to
|
||||
synthesise is reported with `error` (`code: "tts_failed"`) and the request ends with `failed: true`.
|
||||
|
||||
With `--melo-language KR` the MeloTTS child spells numbers out in Hangul before MeloTTS sees them,
|
||||
because its Korean front end misreads them: a number it cannot tag as a counter is read digit by digit
|
||||
(the tag depends on the MeCab build; on Windows "60%" was read "육영퍼센트"), and its own splitter
|
||||
breaks at every dot and comma ("4.2미터" as "사. 이미터"). Decimals are read with 점 and one name per
|
||||
digit after it (사점이), thousands commas are dropped, and every other whole number gets its
|
||||
Sino-Korean reading (육십, 이천이십육), except before a counter MeloTTS reads with native numerals
|
||||
(g2pkk's list: 시, 개, 마리, 살, ...), which stays for MeloTTS ("3시" is 세시).
|
||||
|
||||
Speed starts at `--melo-speed` and `tts_speed` changes it for every sentence made after it (a speed
|
||||
outside 0.5-2.0 or not a number is `bad_message` and the last good one stays). MeloTTS itself speaks
|
||||
up to 1.25: its own speed shortens every sound, and past that it drops them (five Korean sentences,
|
||||
|
||||
Reference in New Issue
Block a user