Stars
Raspberry Pi AI Camera (IMX500) Model Zoo
Solving Rectilinear Steiner Tree Problem(RSTP) using deep learning approach.
Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Graph Neural Network Library for PyTorch
Effective LLM Alignment Toolkit
Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;
Repository with the code for training and evaluating the baseline model of the SynthSOD dataset.
Expressive Anechoic Recordings of Speech (EARS)
Music repair method to convert lossy MP3 compressed music to lossless music.
This repository utilizes the Triton Inference Server Client, which streamlines the complexity of model deployment.
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
Tests to evaluate the support of VHDL 2008 and VHDL 2019 features
Cross-platform, customizable ML solutions for live and streaming media.
A .net 6 implementation to use Yolov5 and Yolov8 models via the ONNX Runtime
Open-Sora: Democratizing Efficient Video Production for All
Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Unofficial implementation of HiFi-GAN+ from the paper "Bandwidth Extension is All You Need" by Su, et al.
Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction
AtomicParsley is a lightweight command line program for reading, parsing and setting metadata into MPEG-4 files, in particular, iTunes-style metadata.
The FFmpeg build script provides an easy way to build a static FFmpeg on OSX and Linux with non-free codecs included.
Official implementation of SAM-Med2D
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…