最新文章

LEANN AI Framework: Lightweight, efficient, adaptive for sustainable AI. Reduces latency 40-60%, ideal for edge/mobile. (LEANN AI框架：轻量、高效、自适应，助力可持续AI。延迟降低40-60%，适用于边缘/移动场景。)

VoxCPM: 0.5B参数语音生成模型，业界领先的自然度与零样本克隆能力。 (VoxCPM: 0.5B参数语音生成模型，业界领先的自然度与零样本克隆能力。)

LEANN AI Framework: A storage-efficient vector search index using dynamic embedding recalculation and compressed graph indices. (LEANN AI框架：采用动态嵌入重算与压缩图索引的高存储效率向量搜索方案。)

LEANN: Embedded vector DB framework for local RAG. On-demand computation & graph-based storage cut 97% space vs. traditional DBs. (LEANN：用于本地RAG的嵌入式向量数据库框架。按需计算和基于图的存储相比传统数据库节省97%空间。)

VoxCPM: 0.5B 端到端 TTS 模型，支持高效本地部署与高质量中文语音合成/克隆。 (VoxCPM: 0.5B端到端TTS模型，支持高效本地部署与高质量中文语音合成/克隆。)

LEANN AI Framework drastically cuts vector index storage to <5% of original size, enabling 50x compression for efficient similarity search. LEANN AI 框架将向量索引存储降至原体积<5%，实现50倍压缩，提升相似性搜索效率。

VoxCPM: Tokenizer-free TTS for context-aware speech & zero-shot voice cloning via continuous diffusion autoregressive modeling. (VoxCPM：通过连续扩散自回归建模实现上下文感知语音和零样本语音克隆的无标记器TTS。)

Pet coughing guide: causes (inflammation, trauma, infection) & how to observe/assist vet diagnosis. (宠物咳嗽指南：解析病因与就医观察要点)

Large AI models: Transformer-based, billions of parameters, self-supervised learning, fine-tunable for tasks. 大型AI模型：基于Transformer，数十亿参数，自监督学习，可针对任务微调。