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
☆11Updated 11 months ago
Alternatives and similar repositories for rkllm_talking
Users that are interested in rkllm_talking are comparing it to the libraries listed below
Sorting:
- 将LLM 模型部署到 Rockchip Rk3588芯片中,在开发板上使用NPU进行推理☆58Updated 11 months ago
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆19Updated last year
- 这是一个用于连接小智AI服务的Python客户端库。它提供了简单的接口来进行语音对话和文本交互。☆22Updated 6 months ago
- An AI chat bot based on volcengine's webRTC protocol.☆29Updated 4 months 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 3 years ago
- ☆17Updated last year
- ☆12Updated 5 months ago
- run chatglm3-6b in BM1684X☆40Updated last year
- Recognize faces and objects in the video based on Milvus.☆22Updated 4 years ago
- Allows access via HTTP to LLM running on RK3588 NPU. Returns JSON response.☆25Updated last year
- 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,…☆156Updated 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
- 小智ESP32服务端配置编辑器是一个图形化工具,专为 xiaozhi-esp32-server 项目设计,旨在简化配置文件的编辑过程。通过直观的界面,用户可以轻松查看和修改 `data/.config.yaml` 文件中的各项配置,无需手动编辑YAML文件。The Xiao…☆26Updated 6 months ago
- 使用OpenCV+onnxruntime部署开放域目标检测,包含C++和Python两个版本的程序☆11Updated last year
- Explore LLM model deployment based on AXera's AI chips☆113Updated last month
- a simple lightweight large language model pipeline framework.☆27Updated 4 months ago
- 本项目为xiaozhi-esp32提供C++后端服务,帮助您快速搭建ESP32设备控制服务器。Backend C++ service for xiaozhi-esp32, helps you quickly build an ESP32 device control ser…☆29Updated 5 months ago
- 使用OpenCV部署图像描述Image_Captioning,包含C++和Python两个版本的程序☆12Updated last year
- ☆29Updated 2 weeks ago
- 使用NCNN推理框架和ByteTrack目标跟踪框架,对网络、文件流URL进行实时性视频推理,而UI界面则由Qt框架实现☆21Updated 11 months ago
- Modify Code From rknn-toolkit2☆54Updated last year
- 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
- Run Large Language Models on RK3588 with GPU-acceleration☆117Updated 2 years ago
- ☆23Updated 4 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☆46Updated 3 years ago
- pose estimation code with deepstream and yolo-pose☆13Updated 2 years ago
- ☆11Updated last year
- Machine vision apps☆38Updated 2 months ago
- Convert the official paddleocr model to a deployable model on RK1126☆38Updated 2 years ago
- ☆79Updated last year