2.14.1

What's new?

• Add support for Depth Anything (https://github.com/xenova/transformers.js/pull/534). See here for the list of available models.

  Example: Depth estimation with Xenova/depth-anything-small-hf.

  import { pipeline } from '@xenova/transformers';
  
  // Create depth-estimation pipeline
  const depth_estimator = await pipeline('depth-estimation', 'Xenova/depth-anything-small-hf');
  
  // Predict depth map for the given image
  const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/bread_small.png';
  const output = await depth_estimator(url);
  // {
  //   predicted_depth: Tensor {
  //     dims: [350, 518],
  //     type: 'float32',
  //     data: Float32Array(181300) [...],
  //     size: 181300
  //   },
  //   depth: RawImage {
  //     data: Uint8Array(271360) [...],
  //     width: 640,
  //     height: 424,
  //     channels: 1
  //   }
  // }

  You can visualize the output with:

  output.depth.save('depth.png');

  Input image	Visualized output

  Online demo: https://huggingface.co/spaces/Xenova/depth-anything-web

  Example video:

  https://github.com/xenova/transformers.js/assets/26504141/bbac3db6-8d8f-4386-a212-7e66ca616a0d

• Fix typo in tokenizers.js (https://github.com/xenova/transformers.js/pull/518)

• Return empty tokens array if text is empty after normalization (https://github.com/xenova/transformers.js/pull/535)

Full Changelog: https://github.com/xenova/transformers.js/compare/2.14.0...2.14.1