Image-to-Text
Transformers
Safetensors
Khmer
khmer-ocr
feature-extraction
transformer
text-recognition
crnn
khmer-text-recognition
custom_code
Instructions to use Darayut/khmer-text-recognition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Darayut/khmer-text-recognition with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="Darayut/khmer-text-recognition", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Darayut/khmer-text-recognition", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| # configuration_khmerocr.py | |
| from transformers import PretrainedConfig | |
| class KhmerOCRConfig(PretrainedConfig): | |
| model_type = "khmer-ocr" | |
| def __init__( | |
| self, | |
| vocab_size=124, | |
| emb_dim=384, | |
| max_global_len=4096, | |
| pad_idx=0, | |
| nhead=8, | |
| num_encoder_layers=2, | |
| num_decoder_layers=2, | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| self.emb_dim = emb_dim | |
| self.max_global_len = max_global_len | |
| self.pad_idx = pad_idx | |
| self.nhead = nhead | |
| self.num_encoder_layers = num_encoder_layers | |
| self.num_decoder_layers = num_decoder_layers | |
| super().__init__(**kwargs) |