swadeshi_hindiwav2vec2asr/ is a Hindi speech recognition model which is a fine tuned version of the theainerd/Wav2Vec2-large-xlsr-hindi model. The model achieved a Word Error Rate of 0.738 when trained with 12 Hours of MUCS data with 30 epochs and given a batch size of 12.
NSDT 3DConvert
Convert 30+ 3D formats online: GLTF, GLB, GBX, OBJ, DAE, IFC, STEP, STL...
UnrealSynth
Unreal engine based photo realistic synthetic data generator for YOLO.
DreamTexture.js
AI powered 3d texture generation and projection SDK for three.js.