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PicoDet目标检测，包含C++和Python两个版本的程序☆30Updated 3 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☆21Updated 2 years ago
- 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
- 学习yolo算法和rknn框架☆36Updated 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
- ☆19Updated 2 years ago
- This project provides simple code and demonstrates how to use the TensorRT C++ API and ONNX to deploy PaddleOCR text recognition model.☆51Updated 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
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆20Updated 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 4 years ago
- RKNN模型推理部署模板☆24Updated 2 years ago
- Convert the official paddleocr model to a deployable model on RK1126☆43Updated 3 years ago
- some ncnn demos of FunASR☆28Updated last year
- a simple lightweight large language model pipeline framework.☆28Updated 9 months ago
- 使用OpenCV部署CoupledTPS，包含了肖像矫正，不规则边界的图像矩形化，旋转图像矫正，三个模型。依然是包含C++和Python两个版本的程序☆20Updated last year
- 基于MNN-llm的安卓手机部署大语言模型：Qwen1.5-0.5B-Chat☆89Updated last year
- 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+onnxruntime部署中文clip做以文搜图，给出一句话来描述想要的图片，就能从图库中搜出来符合要求的图片。包含C++和Python两个版本的程序☆85Updated 2 years ago
- run ChatGLM2-6B in BM1684X☆49Updated last year
- Next Gen Face detection based on YOLOv7☆62Updated 3 years ago
- 基于rknn的官方Android项目rknn_yolov5_android_apk_demo进行修改，部署人脸检测模型retinaface和106人脸关键点检测模型，支持实时人脸检测。支持rk356x和rk3588设备npu推理。☆25Updated last year
- 使用django+pyecharts+PP-Human开发的动态数据大屏, 有人流数据的采集入库, 打架、摔倒等事件警报，口罩检测等实用功能。边缘端版本使用onnx推理提升效率，服务端版本支持视频流推拉☆33Updated 2 years ago
- 在RK3588上使用rknn runtime 推理，使用官方修改过的yolov5模型，mpp解码，rga处理图像，qt5界面显示☆31Updated 7 months ago
- ☆36Updated 6 months ago
- 安卓手机部署DeepSeek-R1 蒸馏的1.5B模型☆23Updated last year
- 使用ONNXRuntime部署PP-YOLOE目标检测，支持PP-YOLOE-s、PP-YOLOE-m、PP-YOLOE-l、PP-YOLOE-x四种结构，包含C++和Python两个版本的程序☆21Updated 3 years ago
- ☆15Updated 2 years ago
- Make a minimal OpenCV runable on any where, WIP☆87Updated 3 years ago
- Multi-thread tracking of YOLOv5 and ByteTrack implemented by C++, accelerated by TensorRT. YOLOv5 和 ByteTrack 的多线程追踪 C++ 实现, 使用 TensorRT …☆82Updated 7 months ago
- ☆20Updated 3 years ago