什么是 Transformers.js？

跨域存储 API 可减少浏览器中模型资源的重复下载和缓存，提升性能。

Transformers.js 可在浏览器中实现图像分类、图像描述和语音转录的多模态 AI，无需服务器或 API 密钥。

ONNX 是一种开放的神经网络交换格式，使模型在不同平台和设备上高效运行，Transformers.js 通过 ONNX 实现跨平台兼容性。

Using Transformers.js to implement practical NLP tasks in the browser, including text classification, zero-shot labeling, and question answering.

Transformers.js 是一个将最先进的机器学习模型引入 JavaScript 的工具，通过 ONNX 格式实现高效推理。

Semantic search can be implemented entirely on the client side using Transformers.js and sentence embeddings, enabling meaning-based retrieval via geometric distance in vector space without any server or API keys.

Tensors are the core data structure in machine learning that convert real-world inputs like text, images, and audio into numerical matrices for computation, producing meaningful outputs. They are simply numbers organized by shape, including scalars (0D), vectors (1D), matrices (2D), and higher-dimensional arrays.

Tensors are fundamental structures in machine learning that organize numbers, enabling models to process real-world data like text, images, and audio by converting them into numerical forms for the complete input-to-output data flow.

Transformers.js implements efficient machine learning inference in JavaScript using ONNX, automatically handling model download, caching, and tensor conversion to simplify Web AI integration.