mmmmayi
Follow
Stars
Pytorch implementation of Extended U-Net for Speaker Verification in Noisy Environments
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
✅ Solutions to LeetCode by Go, 100% test coverage, runtime beats 100% / LeetCode 题解
S3PRL-VC: A Voice Conversion Toolkit based on S3PRL
Keras-based python framework to compute phonological posterior probabilities from audio files
Robust Speech Recognition via Large-Scale Weak Supervision
CRNN Phoneme Recognizer trained with TIMIT
This is a PyTorch implementation of the paper "Attribute Prototype Network for Zero-Shot Learning".
Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021…
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaof…
Removing Adversarial Noise in Class Activation Feature Space
This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.
Noise Conditional Score Networks (NeurIPS 2019, Oral)
Pytorch implementation of Real Time Image Saliency for Black Box Classifiers https://arxiv.org/abs/1705.07857
Real-time image saliency 🌠 (NIPS 2017)
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Self-Supervised Speech Pre-training and Representation Learning Toolkit
Shows visual grounding methods can be right for the wrong reasons! (ACL 2020)
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
SE-Resnet+AMSoftmax for Speaker Verification
Speaker verification using ResnetSE (EER=0.0093) and ECAPA-TDNN
Python client for Moss: A System for Detecting Software Similarity
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.