primepake/wav2lip_288x288
Wav2Lip version 288 and pipeline to train
Implements multi-resolution lip-sync generation (288x288 to 512x512) using SAM-UNet architecture with advanced training techniques including Wasserstein loss, gradient penalty, and PReLU/LeakyReLU activations. Two-stage training pipeline: first trains a SyncNet for audio-visual synchronization, then fine-tunes the Wav2Lip generator with attention-based upsampling. Builds on the original Wav2Lip framework with architectural improvements for higher-quality facial dubbing synthesis.
642 stars. No commits in the last 6 months.
Stars
642
Forks
162
Language
Python
License
MIT
Category
Last pushed
Aug 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/primepake/wav2lip_288x288"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
SARIT42/lipsyncr
LipSyncr is a lip reading web app based on the LipNet model that can lip read videos.
Chris10M/Lip2Speech
A pipeline to read lips and generate speech for the read content, i.e Lip to Speech Synthesis.
Markfryazino/wav2lip-hq
Extension of Wav2Lip repository for processing high-quality videos.
adhadse/Deepdubpy
A complete end-to-end Deep Learning system to generate high quality human like speech in English...
M-SRIKAR-VARDHAN/speech-to-speech-with-lipsync
End-to-end speech-to-speech translation pipeline with voice cloning (RVC) and automatic lip-sync...