• 1
• 0
• 2

o1o2oxxx/CelebAMask-HQ forked from mirrors_switchablenorms/CelebAMask-HQ

A large-scale face dataset for face parsing, recognition, generation and editing.

• 1
• 0
• 12

o1o2oxxx/dev-env-ubuntu forked from cambriconknight/dev-env-ubuntu

构建基于Docker容器的寒武纪开发环境

• 1
• 0
• 11

o1o2oxxx/PlateRecognition forked from pcb9382/PlateRecognition

高性能车牌检测与识别开源代码，方便移植嵌入式和安卓端使用，支持12种车牌识别，支持港澳车牌识别，支持大角度和模糊车牌识别，准确率高达99%+

• 1
• 0
• 1

o1o2oxxx/grouped_gemm forked from la/grouped_gemm

• 1
• 0
• 1

o1o2oxxx/fastrtc forked from ramonly/fastrtc

• 1
• 0
• 7

o1o2oxxx/FaceVerificationSDK forked from FaceAI/FaceAISDK_Android

Android On_device 1:1 Face Recognition And Liveness detection；1:N & M:N Face Search SDK 。 🧒 离线版设备端Android1:1人脸识别 动作活体、静默活体、近红双目外活体检测 以及1:N M:N 人脸搜索 SDK 封装

• 1
• 0
• 1

o1o2oxxx/python-webrtc-audio-processing forked from dengxuezheng/python-webrtc-audio-processing

Python bindings of WebRTC Audio Processing

• 1
• 0
• 0

o1o2oxxx/esp-sr

• 1
• 0
• 3

o1o2oxxx/athena-signal forked from harricHe/athena-signal

北京滴滴公司开源的音频前处理算法库 from: https://github.com/athena-team/athena-signal

• 1
• 0
• 10

o1o2oxxx/esp-skainet forked from 乐鑫开源/esp-skainet

ESP-Skainet 是乐鑫推出的智能语音助手，目前支持唤醒词识别和命令词识别。

• 1
• 0
• 1

o1o2oxxx/Step-Audio forked from 刘凯/Step-Audio

• 1
• 0
• 1

o1o2oxxx/face_verification_experiment forked from mirrors_AlfredXiangWu/face_verification_experiment

• 1
• 0
• 1

o1o2oxxx/diffusers forked from choo/diffusers

• 1
• 0
• 1

o1o2oxxx/opencv_contrib_missing forked from 秦小勤LukeQin/opencv_contrib_missing

安装OpenCV时提示缺少boostdesc_bgm.i文件的问题解决方案。 将以下文件*.i，拷贝到opencv_contrib/modules/xfeatures2d/src/目录下。 将文件夹里的文件test_detectors_regression.impl.hpp，拷贝到opencv_contrib/modules/xfeatures2d/src目录即可

• 1
• 0
• 1

o1o2oxxx/pyAudioAnalysis forked from sjmYuan/pyAudioAnalysis

https://github.com/tyiannak/pyAudioAnalysis-15ffb729e44aa981f360c4b0fa12582007151d81

• 1
• 0
• 1

o1o2oxxx/Audio-Spectrum-Analyzer-in-Python forked from Leonlin/Audio-Spectrum-Analyzer-in-Python

• 1
• 0
• 1

o1o2oxxx/librosa forked from chenmy/librosa

Librosa是一个用于音频、音乐分析、处理的python工具包，一些常见的时频处理、特征提取、绘制声音图形等功能应有尽有，功能十分强大。

• 1
• 0
• 1

o1o2oxxx/ResNeST forked from hchouse/ResNeST

• 1
• 0
• 1

o1o2oxxx/Quantization forked from llbin/Quantization

DEMO:使用PyTorch对模型进行量化