한국어 우선 MeloTTS 웹 서비스 추가 (GPU, 속도/피치, 로그인 없음)

- FastAPI 백엔드: /api/voices, /api/tts, /api/health
- 한국어 메인 + 영어(5종 악센트), 중국어/일본어 UI 제거
- 언어별 목소리 모델 선택, 속도(0.5~2.0x)/피치(±12반음) 조절
- 로그인/사용제한/과금 유도 없음 (무제한 테스트)
- NVIDIA GPU 자동 사용 (torch cu128, Blackwell sm_120)
- 유저 친화 한국어 UI (frontend)
- Docker/compose (GPU 예약), 8788 포트
- MeloTTS(순수 파이썬) 벤더링 + 검증된 버전 고정(constraints)
This commit is contained in:
claude
2026-08-23 21:57:48 +09:00
parent a6f3bac584
commit f197177ae1
77 changed files with 11621 additions and 1 deletions

16
vendor/melo/monotonic_align/__init__.py vendored Normal file
View File

@@ -0,0 +1,16 @@
from numpy import zeros, int32, float32
from torch import from_numpy
from .core import maximum_path_jit
def maximum_path(neg_cent, mask):
device = neg_cent.device
dtype = neg_cent.dtype
neg_cent = neg_cent.data.cpu().numpy().astype(float32)
path = zeros(neg_cent.shape, dtype=int32)
t_t_max = mask.sum(1)[:, 0].data.cpu().numpy().astype(int32)
t_s_max = mask.sum(2)[:, 0].data.cpu().numpy().astype(int32)
maximum_path_jit(path, neg_cent, t_t_max, t_s_max)
return from_numpy(path).to(device=device, dtype=dtype)

46
vendor/melo/monotonic_align/core.py vendored Normal file
View File

@@ -0,0 +1,46 @@
import numba
@numba.jit(
numba.void(
numba.int32[:, :, ::1],
numba.float32[:, :, ::1],
numba.int32[::1],
numba.int32[::1],
),
nopython=True,
nogil=True,
)
def maximum_path_jit(paths, values, t_ys, t_xs):
b = paths.shape[0]
max_neg_val = -1e9
for i in range(int(b)):
path = paths[i]
value = values[i]
t_y = t_ys[i]
t_x = t_xs[i]
v_prev = v_cur = 0.0
index = t_x - 1
for y in range(t_y):
for x in range(max(0, t_x + y - t_y), min(t_x, y + 1)):
if x == y:
v_cur = max_neg_val
else:
v_cur = value[y - 1, x]
if x == 0:
if y == 0:
v_prev = 0.0
else:
v_prev = max_neg_val
else:
v_prev = value[y - 1, x - 1]
value[y, x] += max(v_prev, v_cur)
for y in range(t_y - 1, -1, -1):
path[y, index] = 1
if index != 0 and (
index == y or value[y - 1, index] < value[y - 1, index - 1]
):
index = index - 1