ASR whisper

OpenAI whisper на Македонски јазик

Loss: 0.54 WER: 54

Fine tuning dataset

Common Voice Corpus 11.0

Althoug using an old dataset from 2022 the results show superior performance compared to Wav2Vec 2.0

Convert 30+ 3D formats online: GLTF, GLB, GBX, OBJ, DAE, IFC, STEP, STL...

Unreal engine based photo realistic synthetic data generator for YOLO.

AI powered 3d texture generation and projection SDK for three.js.