Downloads · 30 days
11
23% of all-time downloads
trocr-fonts2
cyttic/trocr-fonts2
trocr-fonts2 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
47
Public
Parameters
299M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026
- SHA
- 3b39d977
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-fonts2
This model is a fine-tuned version of cyttic/exp2-frozen-benyehuda-cont on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4863
- Cer: 0.0256
- Wer: 0.0716
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: 2e-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: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 4.1340 | 0.1290 | 2000 | 1.8493 | 0.1623 | 0.3533 |
| 3.0243 | 0.2581 | 4000 | 1.3591 | 0.1016 | 0.2435 |
| 2.4655 | 0.3871 | 6000 | 1.0782 | 0.0757 | 0.1876 |
| 1.9909 | 0.5161 | 8000 | 0.9080 | 0.0631 | 0.1572 |
| 1.9204 | 0.6452 | 10000 | 0.8012 | 0.0538 | 0.1377 |
| 1.6146 | 0.7742 | 12000 | 0.7248 | 0.0465 | 0.1224 |
| 1.4652 | 0.9032 | 14000 | 0.6544 | 0.0421 | 0.1096 |
| 1.1249 | 1.0323 | 16000 | 0.6225 | 0.0370 | 0.1005 |
| 1.0817 | 1.1613 | 18000 | 0.5926 | 0.0351 | 0.0938 |
| 1.0951 | 1.2903 | 20000 | 0.5625 | 0.0323 | 0.0879 |
| 0.9693 | 1.4194 | 22000 | 0.5366 | 0.0299 | 0.0826 |
| 1.0455 | 1.5484 | 24000 | 0.5129 | 0.0281 | 0.0787 |
| 0.9240 | 1.6774 | 26000 | 0.5037 | 0.0276 | 0.0759 |
| 0.8862 | 1.8065 | 28000 | 0.4911 | 0.0261 | 0.0734 |
| 0.9377 | 1.9355 | 30000 | 0.4868 | 0.0257 | 0.0713 |
| 0.8088 | 2.0 | 31000 | 0.4863 | 0.0256 | 0.0716 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.22.2
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026