onnx

Open-source, offline voice-to-text for macOS. Hold a hotkey, speak, text appears. Private on-device dictation with multiple speech engines.

Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

Local speech-to-text CLI & TUI

Self-hosted, booru-style gallery for a personal image collection

Android keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)

reference pytorch code for intent classification

From-scratch voice agents in Python: end-to-end speech pipelines, runnable chapters, and a small shared library. Local models, explicit streaming behavior.

ONNX-compatible Fast SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.

C# Generative AI SDK - Text, Image, Video and Audio supported

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

.NET library for local embedding generation using ONNX and Microsoft.Extensions.AI

Convert Hugging Face tokenizers to ONNX models for cross-language compatibility (.NET, Java, Python) with embedding models

React Native TurboModule for Sherpa-ONNX offline on-device Speech Processing (STT/TTS/Diarization/VAD) completely offline on the device. Support for Android & iOS

This repository shows various ways of deploying a vision model (TensorFlow) from 🤗 Transformers.

A compiler that transforms computation graphs into the weights of a transformer

Pluggable real-time audio conversation framework for .NET. Local VAD, STT, TTS, and LLM

ONNX speech pipeline library for ASR, diarization, VAD, and denoising

Use Transformers.js from Blazor WebAssembly to run pretrained models with the ONNX Runtime in the browser.

A WebML based Vision-Language App that Roasts you like an Asian Mom