MARS5 speech model (TTS) from CAMB.AI
Open Source Document Management System for Digital Archives
AutoML toolkit for automate machine learning lifecycle
Large-language-model & vision-language-model based on Linear Attention
GLM-4 series: Open Multilingual Multimodal Chat LMs
Serving LangChain LLM apps automagically with FastApi
Build GenAI application quick and easy
Code for the paper Language Models are Unsupervised Multitask Learners
ContextGem: Effortless LLM extraction from documents
SOTA Open Source TTS
Qwen2.5-VL is the multimodal large language model series
AIMET is a library that provides advanced quantization and compression
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster
Management of Yandex Station and other smart home devices
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model
VITS2 backbone with multilingual-bert
A fast TTS architecture with conditional flow matching
SOTA discrete acoustic codec models with 40/75 tokens per second
Advanced techniques for RAG systems
Omnilingual ASR Open-Source Multilingual SpeechRecognition
ChatGPT interface with better UI
Fast and Universal 3D reconstruction model for versatile tasks
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
Official code for Style Aligned Image Generation via Shared Attention
AI discovers 520000 stable inorganic crystal structures for research