Stars
Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"
Fully open reproduction of DeepSeek-R1
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
这是一个Android系统TTS应用,内置微软演示接口,可自定义HTTP请求,可导入其他本地TTS引擎,以及根据中文双引号的简单旁白/对话识别朗读 ,还有自动重试,备用配置,文本替换等更多功能。
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 适配,可用于 key 管理与二次分发。单可执行文件,提供 Docker 镜像,一键部署,开箱即用。LLM API management & k…
NVIDIA Linux open GPU kernel module source
A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.
Assistant for 115 to export download links to aria2-rpc
libco is a coroutine library which is widely used in wechat back-end service. It has been running on tens of thousands of machines since 2013.
A dataset that contains 6,000 non-hair FFHQ portraits.
LightSeq: A High Performance Library for Sequence Processing and Generation
CNN for Chinese Text Classification in Tensorflow
Convolutional Neural Network for Text Classification in Tensorflow
intent detection and slot filling 意图识别与槽填充联合模型
自动聊天软件,支持中英文,采用最新版rasa引擎,可进行意图识别、多轮对话、动作跟踪等功能,自动引导客户消费,应答客户咨询。【Automatic chat software, supporting Chinese and English, using the latest version of Rasa engine, can carry out intention recognition,…
医药知识图谱自动问答系统实现,包括构建知识图谱、基于知识图谱的流水线问答以及前端实现。实体识别(基于词典+BERT_CRF)、实体链接(Sentence-BERT做匹配)、意图识别(基于提问词+领域词词典)。