-
VecxozLab
- Dnipro, Ukraine
- https://www.kaggle.com/vecxoz
Stars
Documented Code for the recreation of a Labelling error in at least one of the TreeAI Object Detection datasets (12_RGB_ObjDet_640_fL). Trees are labeled not as they are described in the Label list.
Repository for the winners of the On Top of Pasketti Children's Speech Recognition Challenge
The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
Tutorial code for the On Top of Pasketti: Children’s Speech Recognition Challenge
A fast and lightweight python-based CTC beam search decoder for speech recognition.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Hackable and optimized Transformers building blocks, supporting a composable construction.
Fast and memory-efficient exact attention
1st Place Solution to ThinkOnward Speed Structure Challenge
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Open tools for Solafune developers and Solafune hackers where can share developed tools in geospatial data.
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Lyra Grapth Tool Package developed by ThinkOnward. This package was developed to aid solving the Off the Beaten Path Challenge.
Model architecture for the ThinkOnward Geophysical Foundation Model
Segmentation models for 3D data with different backbones. PyTorch.
Set of models for classifcation of 3D volumes