Lucy_5 / requirements.txt
aaron
feat: 통합 TTS + 음성 변환 앱 (깨끗한 버전)
2fd89a2
raw
history blame contribute delete
989 Bytes
# Core dependencies (from seed-vc-test)
torch --pre --index-url https://download.pytorch.org/whl/nightly/cu126
torchvision --pre --index-url https://download.pytorch.org/whl/nightly/cu126
torchaudio --pre --index-url https://download.pytorch.org/whl/nightly/cu126
# Audio processing (MeloTTS 호환 버전)
librosa==0.9.1
soundfile==0.12.1
sounddevice==0.5.0
scipy==1.13.1
numpy==1.26.4
pydub==0.25.1
# Machine learning (MeloTTS 호환 버전)
transformers==4.27.4
huggingface-hub
einops==0.8.0
munch==4.0.0
# Text processing (MeloTTS 호환 버전)
nltk==3.8.1
unidic
langid
# Voice conversion specific (Seed-VC 호환 버전)
descript-audio-codec>=1.0.0
modelscope==1.18.1
funasr==1.1.5
# TTS (MeloTTS 호환 버전)
git+https://github.com/myshell-ai/MeloTTS.git
faster-whisper==0.9.0
whisper-timestamped==1.14.2
wavmark==0.0.3
# UI and deployment (최신 안정 버전)
gradio>=4.44.0
spaces
# Utilities (호환 버전)
pyyaml
python-dotenv
matplotlib
hydra-core==1.3.2
requests