Wav2Lip

cd applications
python tools/wav2lip.py \
    --face ../docs/imgs/mona7s.mp4 \
    --audio ../docs/imgs/guangquan.m4a \
    --outfile pp_guangquan_mona7s.mp4 \
    --face_enhancement

preprocessed_root (lrs2_preprocessed)
├── list of folders
|    ├── Folders with five-digit numbered video IDs
|    │   ├── *.jpg
|    │   ├── audio.wav

export CUDA_VISIBLE_DEVICES=0
python tools/main.py --config-file configs/wav2lip.yaml

export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch \
    tools/main.py \
    --config-file configs/wav2lip.yaml \

export CUDA_VISIBLE_DEVICES=0
python tools/main.py --config-file configs/wav2lip_hq.yaml

export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch \
    tools/main.py \
    --config-file configs/wav2lip_hq.yaml \

@inproceedings{10.1145/3394171.3413532,
author = {Prajwal, K R and Mukhopadhyay, Rudrabha and Namboodiri, Vinay P. and Jawahar, C.V.},
title = {A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild},
year = {2020},
isbn = {9781450379885},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3394171.3413532},
doi = {10.1145/3394171.3413532},
booktitle = {Proceedings of the 28th ACM International Conference on Multimedia},
pages = {484–492},
numpages = {9},
keywords = {lip sync, talking face generation, video generation},
location = {Seattle, WA, USA},
series = {MM '20}
}