OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX). Super fast CPU/GPU transcriptions
-
Updated
Jul 3, 2026 - Go
OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX). Super fast CPU/GPU transcriptions
Real-time, lightweight computer vision SDK for detecting eyeglasses using facial landmarks and machine learning. Built for the browser, Node.js, and edge devices via ONNX Runtime and MediaPipe FaceMesh.
unlimited image background remover free to use
Agent-v1: Advanced LLM Agent with Multi-Layer Memory
A worker-pool and model-server toolkit for running vision, embedding, and chat-completion LLM workloads, interfaced through code (not HTTP).
A production-ready framework featuring learnable gates for automated model pruning, achieving 90%+ compression. Supports MobileNetV3, ResNet-18, EfficientNet-B0 with Streamlit dashboard, ONNX export, Docker deployment, and CI/CD. Ideal for AI optimization research and deployment.
This project benchmarks vision (MobileNet, ResNet20) and NLP (DistilBERT) models across server vs. client inference, using backend servers and ONNX-converted local models. It evaluates latency, UX, accuracy, and performance, dedicated to fulfilling the Master’s thesis in AI & ML.
Free AI Background Remover 2026 ✨ | Unlimited & Open Source
Add a description, image, and links to the onxx topic page so that developers can more easily learn about it.
To associate your repository with the onxx topic, visit your repo's landing page and select "manage topics."