bobondemon
Follow
Stars
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
Learn how to use L0 regularization
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Estimating score function for energy-based model using 2D toy examples
Official repository of https://doi.org/10.1109/TASLP.2022.3167258. More up-to-date code is in "refactor" branch.
Offline CGMM and CGMM with spatial prior distribution in an online manner
Some toy examples of score matching algorithms written in PyTorch
Noise Conditional Score Networks (NeurIPS 2019, Oral)
A 10000+ hours dataset for Chinese speech recognition
Towards hot directions in industrial end to end speech recognition
Production First and Production Ready End-to-End Speech Recognition Toolkit
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
Quartznet implementation on pytorch [https://arxiv.org/abs/1910.10261]
李宏毅2021/2022/2023春季机器学习课程课件及作业
Jupyter notebook on Gumbel-max and Gumbel-softmax tricks
A pytorch wrapper for LF-MMI training and parallel training in Kaldi
Hydra is a framework for elegantly configuring complex applications
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
A cross platform front-end GUI of the popular youtube-dl written in wxPython.
Pytorch implementation of Generalized End-to-End Loss for speaker verification
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
PyTorch implementations of Generative Adversarial Networks.
Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition using Pytorch