Blog

The WenetSpeech dataset provides over 10,000 hours of Mandarin Chinese speech, categorized into strong-labeled (10,005 hours), weak-labeled (2,478 hours), and unlabeled (9,952 hours) subsets, suitable

This project develops a small and efficient face recognition system based on the ArcFace and PP-OCRv2 models. The training dataset is emore (containing 85,742 individuals and 5,822,653 images), and th

This project aims to develop a face recognition system with small models, high recognition accuracy, and fast inference speed. The training data is sourced from the emore dataset (5.82 million images)

This project is an end-to-end Automatic Speech Recognition (ASR) system implemented based on Kaldi and MindSpore. The system architecture includes multiple stages such as data collection, preprocessin

This code is mainly based on the PaddlePaddle framework and is used to implement a speech recognition system based on acoustic features. The project structure is clear, including functional modules su

This project demonstrates how to use the PaddlePaddle framework for voiceprint recognition, covering multiple steps from model training to application deployment. The following are some key points and

This project well demonstrates how to use deep learning models for voiceprint recognition and voiceprint comparison. Below, I will optimize and improve the code and provide some suggestions to better

This book provides a detailed introduction to deep learning development using PaddlePaddle, covering the entire process from environment setup to practical project applications. The content includes e

MTCNN is a multi-task convolutional neural network (CNN) for face detection, consisting of three networks: P-Net, R-Net, and O-Net. P-Net generates candidate windows; R-Net performs high-precision fil

This project is a deep learning-based face age and gender recognition system. It uses OpenCV and MTCNN (Multi-Task Cascaded Convolutional Network) for face detection, along with a pretrained model for