加载中…
加载中…
onnx/decoder_model_merged.onnx 159 MBonnx/decoder_model.onnx 159 MBonnx/decoder_with_past_model.onnx 154 MBonnx/encoder_model.onnx 87 MBonnx/decoder_model_merged_fp16.onnx 80 MBonnx/encoder_model_fp16.onnx 44 MBonnx/decoder_model_merged_quantized.onnx 41 MBonnx/decoder_model_quantized.onnx 40 MBonnx/decoder_with_past_model_quantized.onnx 39 MBonnx/encoder_model_quantized.onnx 23 MBhttps://huggingface.co/microsoft/trocr-small-handwritten with ONNX weights to be compatible with Transformers.js.
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @xenova/transformers
Example: Optical character recognition w/ Xenova/trocr-small-handwritten.
import { pipeline } from '@xenova/transformers';
// Create image-to-text pipeline
const captioner = await pipeline('image-to-text', 'Xenova/trocr-small-handwritten');
// Perform optical character recognition
const image = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/handwriting.jpg';
const output = await captioner(image);
// [{ generated_text: 'Mr. Brown commented icily.' }]
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).