Trocr Base Printed
Microsoft's Trocr Base Printed is a chat model with vision capabilities, utilizing an encoder-decoder architecture consisting of an image Transformer and a text Transformer. It is genuinely best at optical character recognition (OCR) on single text-line images, with its image encoder initialized from the weights of BEiT and its text decoder initialized from the weights of RoBERTa.
Input
Output
Context
-
Max Output
-
Parameters
333.3M
Technical Specifications
Model TypeVision
Context WindowNot available
Max Output TokensNot available
Parameters333.3M
Release DateMar 2, 2022
Training CutoffNot available
LicenseMIT
Open SourceYes
Input Modalities
Image
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Trocr Base Printed
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.