AI models
TrOCR
Parameters
558M
Published
Sep 21, 2021
TrOCR is an AI model developed by Beihang University and Microsoft Research Asia (China), first published in September 2021. It works in the vision domain, on tasks such as character recognition (ocr).
Epoch AI has no training-compute estimate for this model. The model has 558,000,000 parameters. Training ran on 32 NVIDIA V100.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 616 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Beihang University, Microsoft Research Asia
- Country of organization
- China
- Domain
- Vision
- Task
- Character recognition (OCR)
- Parameters
- 558,000,000
- Training hardware
- NVIDIA V100
- Chips used
- 32
- Training power draw
- 19.4 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 616
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models