Downloads · 30 days
11
3% of all-time downloads
trocr-medical-v1
nehaMe123/trocr-medical-v1
trocr-medical-v1 is a image-text-to-text model from nehaMe123. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
361
Public
Parameters
334M
95.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt2.7 GB · 50%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- mit
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026
- SHA
- aecc9f97
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
trocr-medical-v1
This model is a fine-tuned version of microsoft/trocr-base-handwritten on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0457
- Cer: 0.4804
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.1551 | 1.0 | 176 | 0.1251 | 0.5190 |
| 0.0726 | 2.0 | 352 | 0.0722 | 0.4774 |
| 0.0601 | 3.0 | 528 | 0.0673 | 0.4916 |
| 0.0419 | 4.0 | 704 | 0.0893 | 0.4804 |
| 0.0123 | 5.0 | 880 | 0.0477 | 0.4744 |
| 0.0193 | 6.0 | 1056 | 0.0789 | 0.4876 |
| 0.0082 | 7.0 | 1232 | 0.0616 | 0.4835 |
| 0.0015 | 8.0 | 1408 | 0.0643 | 0.4901 |
| 0.0008 | 9.0 | 1584 | 0.0522 | 0.4855 |
| 0.0012 | 10.0 | 1760 | 0.0568 | 0.4820 |
| 0.0002 | 11.0 | 1936 | 0.0439 | 0.4789 |
| 0.0001 | 12.0 | 2112 | 0.0449 | 0.4804 |
| 0.0 | 13.0 | 2288 | 0.0456 | 0.4799 |
| 0.0 | 14.0 | 2464 | 0.0457 | 0.4804 |
| 0.0 | 15.0 | 2640 | 0.0457 | 0.4804 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026