mechanicalsea Goto Github PK

dblp-speech

A Python tool access to dblp api, currently supporting publication search and title keyword locate.

docklab

Dockerfile for groups

dynamic-system-rl

using reinforcement learning controls dynamic continuous system

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

kaggle-101-digitrecognizer

Kaggle 平台上练习——手写数字识别。基于随机森林的分类系统，同时测试了 IPCA 对其的影响。

kaggle-101-facialkeypointsdetection

Detect the location of keypoints on face images

kaggle-101-titanic

Kaggle 平台上练习——灾难幸存者分类。基于多种分类方法的组合分类系统，同时额外增加了新的特征。

lighthubert

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

mechanicalsea.github.io

pytorch-light

Easy-to-run Application based on PyTorch

source-tracking-slp

源位置隐私中，研究利用增强学习方法回溯源节点的攻击者，分析其学习性能

spectra

Spectra extraction tutorials based on torch and torchaudio.

sugar

Efficient Speech Processing Tookit for Automatic Speaker Recognition

timit-speaker-identification

Speaker Identification in TIMIT dataset

tools-daily-expense

统计每月的日常支出

voxsrc2020

Competition VoxSRC 2020 - VoxCeleb Speaker Recognition Challenge 2020