ML Video lip synchronization
Budget: €1,500 – €3,000 EUR
Our need would be : from a video of a person (ex: video made from a webcam or other), we would like to be able to associate a lip synch model in real time to make him say something else.
TTS / give a correspondence (viseme / coordinates of the facial landmarks)
We want to use this model : https://github.com/Rudrabha/Wav2Lip
if you have other solutions to propose, feel free to discuss them with us.
Languages supported : french + english
Develop a test html page according to the template we will provide you if you are selected
Provide the code
Provide documentation
TTS / give a correspondence (viseme / coordinates of the facial landmarks)
We want to use this model : https://github.com/Rudrabha/Wav2Lip
if you have other solutions to propose, feel free to discuss them with us.
Languages supported : french + english
Develop a test html page according to the template we will provide you if you are selected
Provide the code
Provide documentation