Downloads · 30 days
7
7% of all-time downloads
trocr-chaghatay
colorlessideas/trocr-chaghatay
trocr-chaghatay is a image-text-to-text model from colorlessideas. 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
98
Public
Parameters
334M
13.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- mit
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Apr 30, 2025
- Updated
- Apr 30, 2025
- SHA
- 504991a0
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-chaghatay
This model is a fine-tuned version of microsoft/trocr-base-handwritten on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3978
- Cer: 0.8823
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.7914 | 0.9948 | 95 | 0.4213 | 0.9869 |
| 0.3869 | 1.9948 | 190 | 0.4202 | 0.9739 |
| 0.3777 | 2.9948 | 285 | 0.3962 | 0.9933 |
| 0.3555 | 3.9948 | 380 | 0.3880 | 0.9999 |
| 0.3512 | 4.9948 | 475 | 0.3807 | 0.9573 |
| 0.3407 | 5.9948 | 570 | 0.3769 | 0.8869 |
| 0.3266 | 6.9948 | 665 | 0.3661 | 0.8941 |
| 0.326 | 7.9948 | 760 | 0.3639 | 0.8975 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Apr 30, 2025
- Updated
- Apr 30, 2025