夜雨飘零's repositories

PPASR

基于PaddlePaddle实现端到端中文语音识别,从入门到实战,超简单的入门案例,超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Language:PythonLicense:Apache-2.0Stargazers:751Issues:10Issues:172

Whisper-Finetune

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

Language:CLicense:Apache-2.0Stargazers:630Issues:7Issues:68

VoiceprintRecognition-Pytorch

This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the same time, this project also supports MelSpectrogram, Spectrogram data preprocessing methods

Language:PythonLicense:Apache-2.0Stargazers:625Issues:7Issues:61

PaddlePaddle-DeepSpeech

基于PaddlePaddle实现的语音识别,中文语音识别。项目完善,识别效果好。支持Windows,Linux下训练和预测,支持Nvidia Jetson开发板预测。

Language:PythonLicense:Apache-2.0Stargazers:621Issues:5Issues:164

MASR

Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。

Language:PythonLicense:Apache-2.0Stargazers:526Issues:10Issues:66

AudioClassification-Pytorch

The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.

Language:PythonLicense:Apache-2.0Stargazers:279Issues:6Issues:25

VoiceprintRecognition-Tensorflow

使用Tensorflow实现声纹识别

Language:PythonLicense:Apache-2.0Stargazers:278Issues:4Issues:24

VoiceprintRecognition-PaddlePaddle

本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型,同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法

Language:PythonLicense:Apache-2.0Stargazers:184Issues:5Issues:10

ClassificationForAndroid

在Android使用深度学习模型实现图像识别,本项目提供了多种使用方式,使用到的框架如下:Tensorflow Lite、Paddle Lite、MNN、TNN

Language:C++License:Apache-2.0Stargazers:151Issues:4Issues:9

Pytorch-MTCNN

基于Pytorch实现的MTCNN模型,人脸检测,人脸关键点检测。

Language:PythonLicense:Apache-2.0Stargazers:120Issues:3Issues:6

PunctuationModel

中文标点符号模型,可以给文本添加标点符号。

Language:PythonLicense:Apache-2.0Stargazers:110Issues:4Issues:17

VoiceprintRecognition-Keras

基于Kersa实现的声纹识别模型

Language:PythonLicense:Apache-2.0Stargazers:110Issues:4Issues:4

PP-YOLOE

PaddlePaddle实现的目标检测模型PP-YOLOE

Language:PythonLicense:Apache-2.0Stargazers:101Issues:3Issues:13

Pytorch-MobileFaceNet

Pytorch实现的人脸识别明细MobileFaceNet模型,在预测使用MTCNN检测人脸,然后使用MobileFaceNet模型识别。

Language:PythonLicense:Apache-2.0Stargazers:96Issues:2Issues:10

SpeechEmotionRecognition-Pytorch

基于Pytorch实现的语音情感识别

Language:PythonLicense:Apache-2.0Stargazers:85Issues:4Issues:2

AudioClassification-PaddlePaddle

基于PaddlePaddle实现的音频分类,支持EcapaTdnn、PANNS、TDNN、Res2Net、ResNetSE等各种模型,还有多种预处理方法

Language:PythonLicense:Apache-2.0Stargazers:77Issues:4Issues:7

PaddlePaddle-MobileFaceNets

PaddlePaddle实现的人脸识别模型MobileFaceNets,在预测的是使用MTCNN检测人脸,然后MobileFaceNets模型识别。

Language:PythonLicense:Apache-2.0Stargazers:54Issues:1Issues:2

PaddlePaddle-SSD

基于PaddlePaddle实现的SSD,包括MobileNetSSD,MobileNetV2SSD,VGGSSD,ResNetSSD

Language:PythonLicense:Apache-2.0Stargazers:54Issues:2Issues:1

Tensorflow-FaceRecognition

基于MTCNN和MobileFaceNet实现的人脸识别,提供三种预测方式,满足各种需求 。

Language:PythonLicense:Apache-2.0Stargazers:53Issues:5Issues:3

PaddlePaddle-CrowdNet

基于PaddlePaddle实现的人流密度识别模型CrowdNet

Language:PythonLicense:Apache-2.0Stargazers:44Issues:1Issues:2

FaceKeyPointsMask

人脸检测、口罩识别、关键检测

Language:JavaLicense:Apache-2.0Stargazers:40Issues:2Issues:2
Language:PythonLicense:Apache-2.0Stargazers:31Issues:2Issues:2

ChangeHumanBackground

人物更换背景

Language:JavaLicense:Apache-2.0Stargazers:22Issues:3Issues:1

Chinese-LLM-Chat

大语言模型微调的项目,包含了使用QLora微调ChatGLM和LLama

Language:PythonLicense:Apache-2.0Stargazers:18Issues:2Issues:2

VITS-Pytorch

本项目是基于Pytorch的语音合成项目,使用的是VITS,VITS是一种语音合成方法,这种时端到端的模型使用起来非常简单,不需要文本对齐等太复杂的流程,直接一键训练和生成,大大降低了学习门槛。

Language:PythonLicense:Apache-2.0Stargazers:16Issues:0Issues:0

CameraXApp

CameraX实现的相机

Language:KotlinLicense:Apache-2.0Stargazers:12Issues:0Issues:0
License:Apache-2.0Stargazers:11Issues:2Issues:0

VITS-PaddlePaddle

本项目是基于PaddlePaddle的语音合成项目,使用的是VITS,VITS是一种语音合成方法,这种时端到端的模型使用起来非常简单,不需要文本对齐等太复杂的流程,直接一键训练和生成,大大降低了学习门槛。

Language:PythonLicense:Apache-2.0Stargazers:3Issues:0Issues:0

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

Language:PythonLicense:NOASSERTIONStargazers:2Issues:0Issues:0

yeyupiaoling.github.io

夜雨飘零的个人博客

Language:HTMLStargazers:2Issues:2Issues:0