GitHub

This is a 288x288 wav2lip model version. Some Features I will implement here

I trained my own model on AVSPEECH dataset and then transfer learning with my private dataset.

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
checkpoints		checkpoints
evaluation		evaluation
face_detection		face_detection
filelists		filelists
models		models
results		results
temp		temp
README.md		README.md
audio.py		audio.py
clear_data.py		clear_data.py
collect_avspeech.py		collect_avspeech.py
color_syncnet_train.py		color_syncnet_train.py
convert2fps.py		convert2fps.py
hparams.py		hparams.py
hq_wav2lip_train.py		hq_wav2lip_train.py
inference.py		inference.py
preprocess.py		preprocess.py
requirements.txt		requirements.txt
wav2lip_train.py		wav2lip_train.py

Provide feedback