VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- 43k
- Python
- Apache-2.0
- 13 d ago
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
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
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
Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model validation records, Swift examples through CoreAIKit, and a downloadable Mac app.
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.
Explore LLM model deployment based on AXera's AI chips, It provides OpenAI‑compatible APIs and supports AX620E, AX650 and AX637 series chips.
Text generation model, used with transformers.
Text classification model, used with sentence-transformers.
Image text to text model, used with gguf.
本地 LaTeX 工作台:源码/PDF 双栏、图片识别、保真语法修复、AgentSkills 与人工审阅 · AGPL-3.0-only
Text generation model, used with transformers.
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
A multi-agent trading firm powered by small language models
Runs in the browser on Hugging Face
An old radio that picks up parallel universes, live
Runs in the browser on Hugging Face
PicQ: Demo for MiniCPM-o 4.5 to answer questions about images using natural language.
⚡ A talking desktop Pikachu that runs 100% on-device — MiniCPM5-1B brain + VoxCPM voice + Nemotron ears, every model ≤1B params. No cloud, works with the Wi-Fi off.
VidiQA: Demo for MiniCPM-o 4.5 to answer questions about videos using natural language.
Local ≤3B assistant that writes & verifies HA automations
Runs in the browser on Hugging Face
Local AI assistant for reviewing suspicious Pakistani notices and messages with MiniCPM, Nemotron-Parse, and Docker CUDA support.
OCR/IDP + ERP NLQ chatbot on small models (MiniCPM)
Runs in the browser on Hugging Face
Small model reads financials; engine catches OCR errors
Runs in the browser on Hugging Face
Research prototype: a small local LLM reads a long document once and keeps only what a question needs, using single-token decisions and prefix-cache reuse.
Benchmarking Edge-Based Large Models with Fewer Than 40 Billion Parameters. Includes updated models from vendors such as qwen, minicpm, Ornith, Spark, gemma, Ling, LFM, and RWKV.
An innovative anomaly detection system for manufacturing industries. Integrating MVTec AD dataset, MiniCPM language model, and LoRA explanation generation, achieving AUC 0.7175 practical-level anomaly detection performance on 416 complete wallplugs dataset.