lipsynth-experiment
Jupyter Notebook
★ 2
updated 2y ago
End-to-end pipeline generates speech from silent lip videos using LLMs and audio-visual cues, combining "AVI-Talking" and "Towards Accurate Lip-to-Speech Synthesis in-the-Wild" techniques, enabling synthesis from visual cues alone without audio/transcripts.
No plain-English explanation yet — one is being written right now. Check back in a minute.