SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Audio transcription using mlx whisper and vad silence processing

Implementation of the Descript Audio Codec in MLX

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

TTS with kokoro and onnx runtime

Super simple MLX (apple silicon) CLIP based photo similarity web app

MLX implementation of xLSTM model by Beck et al. (2024)

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.

A fast multimodal LLM for real-time voice

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

mlx image models for Apple Silicon machines

Efficient framework-agnostic data loading

Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seaml…

MLX support for the Open Neural Network Exchange (ONNX)

Large Concept Models: Language modeling in a sentence representation space

📋 NotebookMLX - An Open Source version of NotebookLM (Ported NotebookLlama)

Blazing fast whisper turbo for ASR (speech-to-text) tasks

MLX: An array framework for Apple silicon

Fast and accurate automatic speech recognition (ASR) for edge devices