OutofLipSync / requirements.txt
alex
minor cleanup
bac2101
# --- Core Torch Stack ---
torchaudio==2.8.0
torchvision==0.23.0
triton
deepspeed==0.17.1
flash-attn-3 @ https://huggingface.co/alexnasa/flash-attn-3/resolve/main/128/flash_attn_3-3.0.0b1-cp39-abi3-linux_x86_64.whl
indextts @ git+https://github.com/OutofAi/index-tts-batch.git
latentsync @ git+https://github.com/OutofAi/LatentSync-batch.git
pyannote.audio
ctranslate2
faster-whisper
pydub==0.25.1
srt
audio-separator==0.24.1
ffmpeg-python==0.2.0
python_speech_features==0.6
librosa==0.10.2.post1 # higher than 0.10.1
accelerate==1.8.1
transformers==4.52.3
tokenizers==0.21.0
sentencepiece
g2p-en==2.1.0
cn2an==0.5.22
textstat
omegaconf==2.3.0
munch==4.0.0
tqdm
json5==0.10.0
diffusers==0.33.1
huggingface-hub<1.0
imageio==2.27.0
decord==0.6.0
opencv-python==4.9.0.80 # same version, deduped
mediapipe==0.10.11
av
torch-fidelity==0.3.0
torchmetrics==1.3.1
lpips==0.1.4
face-alignment==1.4.1
insightface==0.7.3
kornia==0.8.0
scenedetect==0.6.1
moviepy==1.0.3
# --- Numerical / Scientific ---
numpy==1.26.2 # higher than 1.24.4
matplotlib==3.8.2
numba==0.58.1
Cython==3.0.7
einops==0.7.0
ninja==1.11.1.1
# --- Model Repos & Tools ---
descript-audiotools @ git+https://github.com/descriptinc/audiotools.git
tigersound @ git+https://github.com/OutofAi/tigersound.git
tensorboard
hf-xet==1.1.8
DeepCache==0.1.1
ultralytics
batch-face
modelscope==1.27.0
onnxruntime-gpu==1.21.0
# --- Language-specific packages ---
jieba==0.42.1
# --- Environment-specific ---
WeTextProcessing; platform_machine != "Darwin"
wetext; platform_system == "Darwin"