carykh/videoToVoice
takes in a sequence of lip images, and predicts the phonemes being said.
PythonMIT
Stargazers
- aarcangeliModena, Italy
- AlephFive@ColgateHCI @borderxlab @Cardinalidea
- AstloFrance
- cubedhuang@lynk-holdings
- cyboerg42Next Ĺayer GmbH
- DwynDwe
- Evans-OkerosiDmension Data Solutions
- fr3fou@pushmarket
- generic-github-userUnited States
- geofmureithi-zzNairobi, Kenya
- harrypotter0@SicRas
- HillcrestEnigmaCanada
- imlatefortheshowVampy's Castle
- indiestShanghai, China
- JaschanChile
- jdawson4
- johndpopeSydney
- justalemonSantiago, Chile
- katyperry13
- KeithPetroSaskatoon, Saskatchewan
- KoolenDasheppi
- larsmhar
- leeproLambdaWorks / OikoLab
- littletsu@vrienstudios
- neiblaAuckland, New Zealand
- NitroGuy10
- nm17Russian Federation
- pedrofracassi@WarlocksTech
- pniedzwiedzinskiPoznań, Poland
- ppasupat
- rndtrash@TeaSanctuary
- SlyEchoTallinn
- theWebby
- Thijmenvis
- vivian-ng
- zurpNineSix