A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
- apple-silicon
- audio-processing
- mlx
- multimodal
142,273 visible repositories in the index
265–288 of 3,312 · Most stars
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
The Open edX LMS & Studio, powering education sites around the world!
BertViz: Visualize Attention in Transformer Models
Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.
TranslatedOpen-source manuscript of 《深入理解 AI Infra:量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
A fast PostgreSQL Database Client Library for Python/asyncio.
🚴 Call stack profiler for Python. Shows you why your code is slow!
Create reusable templates and turn them into configurable workloads for homelabs and self-hosted infrastructure. Free and Open-Source.
Flagsmith is an open-source feature flag platform with remote config and experimentation. Choose from self-hosted or cloud deployment options.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Automagically synchronize subtitles with video.
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
A framework for efficient model inference with omni-modality models
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
TranslatedAsynchronous multi-platform chatbot framework written in Python
BIOS and firmware files for emulators, put in the right folder and checked: RetroArch, Batocera, Recalbox, EmuDeck, RetroBat, RetroDECK, Lakka, RetroPie, RomM, ROCKNIX, MiSTer and more. One-line installer or ZIP pack.
TranslatedSelf-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
A supercharged Git/GitHub command line interface (CLI). An official integration for GitHub and GitHub Enterprise: https://github.com/works-with/category/desktop-tools
Thirteen Claude skills that run an Instagram account: Reels off 26 scored hook formulas, a viral research skill, a caption linter, and a humanizer. Free, MIT.
Chromium fork named after radioactive element No. 90. Source code and Linux releases. Windows/MacOS/ARM builds served in different repos, links are towards the top of the README.md.
A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system helps you research, write, analyze, and optimize content that ranks well and serves your target audience.
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.