EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction

Open-Source Grammarly Alternative

Schedule-Free Optimization in PyTorch

Things you can do with the token embeddings of an LLM

Cross-platform, customizable ML solutions for live and streaming media.

Simple (and cheap!) neural network uncertainty estimation

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

On-device Speech Recognition for Apple Silicon

A project that optimizes Whisper for low latency inference using NVIDIA TensorRT

NVActivityIndicatorView implemented in SwiftUI

NSGA2, NSGA3, R-NSGA3, MOEAD, Genetic Algorithms (GA), Differential Evolution (DE), CMAES, PSO

Bridges UIKit presentation APIs to a SwiftUI API so you can use presentation controllers, interactive transitions and more.

L2O/NCO codes from CIAM Group at SUSTech, Shenzhen, China

Official implementation of IJCAI'24 paper "Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy"

Official Implementation of the paper: INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer

implementation of our IJCAI'24 paper "Cross-Problem Learning for Solving Vehicle Routing Problems".

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Pytorch implementation of set transformer

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

A set of Python scripts that makes your experience on TPU better

Floating Label TextField for SwiftUI. FloatingLabelTextFieldSwiftUI

Kolors Team

A modular graph-based Retrieval-Augmented Generation (RAG) system

Laminar - Open-source DataDog + PostHog for AI agents / RAG apps. Fast, reliable and insightful. Written in Rust 🦀. YC S24.

Beginner-friendly introduction to TensorRT using Torch-TRT on YOLO-V5