Ming-omni-tts: A Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control

Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Production First and Production Ready End-to-End Speech Recognition Toolkit

📚 Freely available programming books

虚拟爱抖露(アイドル)共享计划, 是基于单目RGB摄像头的人眼与人脸特征点检测算法, 在实时3D面部捕捉以及模型驱动领域的应用.

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

SpellGCN

手写实现李航《统计学习方法》书中全部算法

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

This repository is for the paper "Confusionset-guided Pointer Networks for Chinese Spelling Check"

This repository is for the paper "A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check"

speech emotion recognition using a convolutional recurrent networks based on IEMOCAP

CRF++: Yet Another CRF toolkit

Python PDF Parser

ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典