f197177ae1
- 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)
36 lines
1.2 KiB
Python
36 lines
1.2 KiB
Python
from . import chinese, japanese, english, chinese_mix, korean, french, spanish
|
|
from . import cleaned_text_to_sequence
|
|
import copy
|
|
|
|
language_module_map = {"ZH": chinese, "JP": japanese, "EN": english, 'ZH_MIX_EN': chinese_mix, 'KR': korean,
|
|
'FR': french, 'SP': spanish, 'ES': spanish}
|
|
|
|
|
|
def clean_text(text, language):
|
|
language_module = language_module_map[language]
|
|
norm_text = language_module.text_normalize(text)
|
|
phones, tones, word2ph = language_module.g2p(norm_text)
|
|
return norm_text, phones, tones, word2ph
|
|
|
|
|
|
def clean_text_bert(text, language, device=None):
|
|
language_module = language_module_map[language]
|
|
norm_text = language_module.text_normalize(text)
|
|
phones, tones, word2ph = language_module.g2p(norm_text)
|
|
|
|
word2ph_bak = copy.deepcopy(word2ph)
|
|
for i in range(len(word2ph)):
|
|
word2ph[i] = word2ph[i] * 2
|
|
word2ph[0] += 1
|
|
bert = language_module.get_bert_feature(norm_text, word2ph, device=device)
|
|
|
|
return norm_text, phones, tones, word2ph_bak, bert
|
|
|
|
|
|
def text_to_sequence(text, language):
|
|
norm_text, phones, tones, word2ph = clean_text(text, language)
|
|
return cleaned_text_to_sequence(phones, tones, language)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
pass |