Downloads · 30 days
8
2% of all-time downloads
trocr-handwritten-medical
nehaMe123/trocr-handwritten-medical
trocr-handwritten-medical is a machine learning model from nehaMe123. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
357
Public
Parameters
334M
5.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- License
- mit
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026
- SHA
- 25d14401
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-handwritten-medical
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: 0.0924
- Cer: 0.0151
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.6097 | 1.0 | 757 | 0.2678 | 0.0534 |
| 0.2218 | 2.0 | 1515 | 0.1831 | 0.0367 |
| 0.1264 | 3.0 | 2272 | 0.1424 | 0.0286 |
| 0.0594 | 4.0 | 3030 | 0.1026 | 0.0165 |
| 0.0239 | 5.0 | 3785 | 0.0924 | 0.0151 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.8.0+cu126
- Datasets 2.18.0
- Tokenizers 0.15.2
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026