Downloads · 30 days
7
17% of all-time downloads
TrOCR_0208-1
yoon1000/TrOCR_0208-1
TrOCR_0208-1 is a image-text-to-text model from yoon1000. 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
42
Public
Parameters
385M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Feb 8, 2024
- Updated
- Feb 8, 2024
- SHA
- 0e489119
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_0208-1
This model is a fine-tuned version of microsoft/trocr-base-stage1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8777
- Cer: 0.0931
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.5571 | 0.68 | 200 | 1.6487 | 0.2024 |
| 0.9405 | 1.37 | 400 | 1.2816 | 0.1666 |
| 0.6927 | 2.05 | 600 | 1.0319 | 0.1199 |
| 1.0794 | 2.74 | 800 | 0.8777 | 0.0931 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.13.0
- Tokenizers 0.15.0
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- Created
- Feb 8, 2024
- Updated
- Feb 8, 2024