Downloads · 30 days
18
33% of all-time downloads
trocr-small-BY5-stage1-gated
cyttic/trocr-small-BY5-stage1-gated
trocr-small-BY5-stage1-gated is a image-text-to-text model from cyttic. 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
54
Public
Parameters
235M
2.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors940 MB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- mit
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Sep 19, 2026
- Updated
- Oct 30, 2026
- SHA
- 7415d26b
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-small-BY5-stage1-gated
This model is a fine-tuned version of cyttic/trocr-hebrew-small-untrained on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.1414
- Cer: 0.7721
- Wer: 1.1924
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 1550
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 13.6573 | 0.1290 | 2000 | 6.5881 | 0.8174 | 1.3414 |
| 12.7941 | 0.2581 | 4000 | 6.3714 | 0.7781 | 1.1430 |
| 12.9810 | 0.3871 | 6000 | 6.3217 | 0.8099 | 1.2750 |
| 12.7226 | 0.5161 | 8000 | 6.2336 | 0.7737 | 1.1304 |
| 12.5489 | 0.6452 | 10000 | 6.1967 | 0.7865 | 1.1806 |
| 12.7069 | 0.7742 | 12000 | 6.1668 | 0.7863 | 1.1763 |
| 12.6142 | 0.9032 | 14000 | 6.1480 | 0.7714 | 1.1946 |
| 12.3996 | 1.0 | 15500 | 6.1414 | 0.7721 | 1.1924 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.1
- Tokenizers 0.22.2
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Sep 19, 2026
- Updated
- Oct 30, 2026