Starred repositories
Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…
Production-grade client-side tracing, profiling, and analysis for complex software systems.
A library for exporting models including NeMo and Hugging Face to optimized inference backends, and deploying them for efficient querying
This tool helps you easily deploy ASR models on NPUs on AMD's Ryzen AI 300 series laptops
Next.js running in Electron: the best way to develop desktop apps
A framework for efficient model inference with omni-modality models
TTS model capable of streaming conversational audio in realtime.
A PyTorch native platform for training generative AI models
Develop Desktop, Embedded, Mobile and WebAssembly apps with C# and XAML. The most popular .NET UI client technology
A free, open source, and extensible speech-to-text application that works completely offline.
An MLX/CoreML implementation of SimulStreaming. ~15x increase in performance
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Drax: Speech Recognition with Discrete Flow Matching
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Hierarchical Korean-English Code-Switching Speech Recognition Benchmark (Under Review) | 한영 혼용 음성인식 벤치마크
Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)
Generative AI extensions for onnxruntime
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Python tool for converting files and office documents to Markdown.