[CVPR 2026] Official Implementation of Dynamic erf (Derf).

Simple internal event bus for Go applications

Official python client for Mythic Infinity.

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

5X faster 60% less memory QLoRA finetuning

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

Versatile audio super resolution (any -> 48kHz) with AudioSR.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

The Open Source BlitzMax Compiler Project

A pipeline parallel training script for LLMs.

Run Mixtral-8x7B models in Colab or consumer desktops

Training LLMs with QLoRA + FSDP

A Gradio UI for XTTSv2 and RVC.

Easily train a good VC model with voice data <= 10 mins!

Train the next generation of TTS systems.

Fine Tune the Style-TTS2 Voice Model

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

RayLLM - LLMs on Ray (Archived). Read README for more info.

Async database support for Python. 🗄

MLX: An array framework for Apple silicon

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

Experimental adventure game with AI-generated content

An async Python micro framework for building web applications.

Go ahead and axolotl questions

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

PyTorch code and models for the DINOv2 self-supervised learning method.

Performant and accurate speech recognition built on Pytorch

A fork of the Official implementation of AnimateDiff.