Instructions to use Xenova/trocr-small-printed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/trocr-small-printed with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-to-text', 'Xenova/trocr-small-printed');
about trocr retrained model onnx conversion
#2
by sainithish - opened
how to convert my fine tune model to encoder.onnx , decoder.onnx? also how to quantize onnx mdoels
sainithish changed discussion title from retrained model onnx conversion to about trocr retrained model onnx conversion
thanks and also letme know if possible, first i have tried with microsoft/trocr-small-printed model onnx conversion, inference also working nice as same as before onnx conversion, but problem with fine tune model, after onnx converted model results not good as compare with before onnx conversion.