Trocr Base Handwritten
Microsoft's Trocr Base Handwritten is a chat model with vision capabilities, specifically designed for optical character recognition (OCR) tasks, particularly exceling at recognizing text in single text-line images. Its architecture is notable for utilizing an encoder-decoder structure, combining an image Transformer encoder initialized from BEiT weights with a text Transformer decoder initialized from RoBERTa weights.
Input
Output
Context
-
Max Output
-
Parameters
334M
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Trocr Base Handwritten
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.