dadDR / rkllm_talkingLinks
rkllm_talking is a standalone compiled voice communication system based on a large model || rkllm_talking 是一个独立编译的基于大模型的语音交流系统
☆12Updated last year
Alternatives and similar repositories for rkllm_talking
Users that are interested in rkllm_talking are comparing it to the libraries listed below
Sorting:
- 使用ONNXRuntime部署Detic检测2万1千种类别的物体，包含C++和Python两个版本的程序☆17Updated 2 years ago
- 使用OpenCV部署L2CS-Net人脸朝向估计，包含C++和Python两个版本的程序，只依赖opencv库就可以运行☆20Updated 2 years ago
- some ncnn demos of FunASR☆28Updated last year
- 在瑞芯微rockchip的AI芯片rv1109上，利用rknn和opencv库，修改了官方yolov3后处理部分代码Bug，交叉编译yolov3-demo示例后可成功上板部署运行。☆34Updated 4 years ago
- deploy onnx models with TensorRT and LibTorch☆19Updated 4 years ago
- ppstructure deploy by ncnn☆35Updated last year
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆19Updated last year
- 使用OpenCV部署图像描述Image_Captioning，包含C++和Python两个版本的程序☆12Updated 2 years ago
- run chatglm3-6b in BM1684X☆39Updated last year
- 基于rknn的yolov5的cpp实现，包含各种依赖库，是一个完整工程，可直接编译运行☆21Updated 3 years ago
- A high performance, high expansion, easy to use framework for AI application. 为AI应用的开发者提供一套统一的高性能、易用的编程框架，快速基于AI全栈服务、开发跨端边云的AI行业应用，支持GPU，…☆160Updated last year
- Explore LLM model deployment based on AXera's AI chips☆136Updated this week
- 使用OpenCV部署眼睛凝视估计，包含C++和Python两个版本的程序，只依赖opencv库就可以运行，彻底摆脱对任何深度学习框架的依赖。☆16Updated 2 years ago
- RKNN模型推理部署模板☆25Updated 2 years ago
- Utilizes ONNX Runtime for TTS model.☆45Updated this week
- SummerAsr 是一个基于C++的可独立编译且几乎没有额外依赖库的本地中文语音识别器。 Summer Asr is a Chinese automatic speech recognize project written with C++ that can be eas…☆101Updated last year
- 使用ONNXRuntime部署PicoDet目标检测，包含C++和Python两个版本的程序☆30Updated 3 years ago
- a simple lightweight large language model pipeline framework.☆28Updated 8 months ago
- 使用onnxruntime部署LYT-Net轻量级低光图像增强，包含C++和Python两个版本的程序☆29Updated last year
- Convert the official paddleocr model to a deployable model on RK1126☆43Updated 3 years ago
- The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588☆48Updated 3 years ago
- 使用onnxruntime部署实时视频帧插值，包含C++和Python两个版本的程序☆28Updated last year
- 使用ONNXRuntime部署DeDoDe："局部特征匹配：检测，不要描述——描述，不要检测"。依然是C++和Python两个版本的程序☆23Updated 2 years ago
- 基于MNN-llm的安卓手机部署大语言模型：Qwen1.5-0.5B-Chat☆89Updated last year
- Recognize faces and objects in the video based on Milvus.☆22Updated 4 years ago
- 高效部署：YOLO X, V3, V4, V5, V6, V7, V8, EdgeYOLO TRT推理 ™️ ,前后处理均由CUDA核函数实现 CPP/CUDA🚀☆53Updated 2 years ago
- 万物检测（零样本检测+识别） demo for SG2300X 【Recognize Anything + GroundingDINO】☆24Updated last year
- ☆25Updated 4 years ago
- ☆16Updated 4 years ago
- qwen2 and llama3 cpp implementation☆49Updated last year