VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

A powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

Cook up amazing AI applications effortlessly with MiniCPM / MiniCPM-V / MiniCPM-o

MiniCPM-V apps — fully offline multimodal chat on iOS / Android / HarmonyOS

Community model zoo for Apple Core AI (iOS/macOS 27): 49 models — LLM, VLM, OCR, ASR, TTS, image/video/music gen, forecasting — converted, verified on real devices, downloadable from Hugging Face, and runnable in one line of Swift via CoreAIKit. Plus conversion recipes, on-device benchmarks, custom Metal kernels, and a knowledge base.

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

Explore LLM model deployment based on AXera's AI chips

A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captioning and visual analysis.

Advanced Android photo editor powered by on-device AI models (LaMa, EdgeSAM, MobileViT) with GPU-accelerated adjustments, voice commands, generative fill, and professional editing tools. Built with Jetpack Compose and ONNX Runtime for fast, offline-first image processing.

CRNN/LPRNet/STNet + CTC + CCPD

MaskClaw项目构建了一套基于端侧多模态大模型的自进化隐私防护架构，通过视觉脱敏与Agentic 规则演进，实现了 Agent 行为偏好与隐私防护策略的动态协同生长，确保了高危隐私数据在云端交互中的物理级安全与个体化适配。

为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字

PicQ: Demo for MiniCPM-o 4.5 to answer questions about images using natural language.

Generate realistic speech and clone voices in ComfyUI with VoxCPM custom nodes, featuring token-free TTS, style guidance, and LoRA training support.

Build voice apps fast. Unified API for speech recognition & synthesis with streaming, WebSocket, and multi-engine support.

Grounded Semantic Role Labeling for Human–Robot Interaction — synthetic multimodal data generation and MiniCPM-V training for grounded command understanding. (EMNLP 2025)