Easy to use Beamformers for multi-channel speech separation/enhancement

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

A MLX port of FLUX based on the Huggingface Diffusers implementation.

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

A formalized proof of Carleson's theorem in Lean

Reference implementations of several LangChain agents as Streamlit apps

Convert PDF to markdown quickly with high accuracy

SpeechGPT Series: Speech Large Language Models

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Agent Zero AI framework

Fast & Simple repository for pre-training and fine-tuning T5-style models

Ongoing Lean formalisation of the proof of Fermat's Last Theorem

A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.

The memory layer for Personalized AI

Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

Official Repository for the Uni-Mol Series Methods

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快

SimPO: Simple Preference Optimization with a Reference-Free Reward

simple delaysum, MVDR and CGMM-MVDR

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Code for ACL 2024 findings paper "CTC-based Non-autoregressive Textless Speech-to-Speech Translation"

Ready to run PyTorch implementation of Data2Vec 2.0: Highly efficient self-supervised representation learning for vision, speech and text.

Efficient Low-Memory Aligner

Code for AAAI 2021 paper "Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance"

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

LLM101n: Let's build a Storyteller