Stars
A talking LLM that runs on your own computer without needing the internet.
This project contains various python scripts used in YouTube videos.
A nearly-live implementation of OpenAI's Whisper, using sounddevice. Requires existing Whisper install.
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
kaldi-asr/kaldi is the official location of the Kaldi project.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
React app for inspecting, building and debugging with the Realtime API
Count the MACs / FLOPs of your PyTorch model.
Visualizer for neural network, deep learning and machine learning models
A shared library of on-demand DeepStream Pipeline Services for Python and C/C++
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
An MIT License of YOLOv9, YOLOv7, YOLO-RD
NVIDIA DeepStream SDK 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
Conversion utility for Label Studio video annotations to a YOLO-compatible format, including bounding box interpolation
We write your reusable computer vision tools. 💜
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
A computer algebra system written in pure Python
Deep learning-based mobile model deployment(Object Tracking). Lightweight Object Tracking, NCNN,
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Source code for an Computer Vision and Deep Learning based algorihtm to detect and tracking UAVs from camera mounted on a flying UAV.
Second Rank achiever code in Bird vs Drone during WOSDETC 2023 workshop at ICASSP 2023
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Simple Online Realtime Tracking with a Deep Association Metric
A plugin for Unity that lets you access Streaming Assets directly on Android.
Phase shifting algorithms for encoding and decoding sinusoidal fringe patterns.
darktable is an open source photography workflow application and raw developer