Image-to-Text
Transformers
Safetensors
Khmer
English
khmer-ocr
feature-extraction
ocr
text-recognition
khmer-text-recognition
transformer
squeeze-and-excitation
netra-lab
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)# pip install -U transformers accelerate # 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
Commit History
16 days ago
-
Update model card: smaller logo header, blockwise decoding figure, refreshed results chart
Verified signature1be88cc
-
Update model card for the cluster-vocabulary model and netra-ocr 1.1.0
Verified signatureDocuments the current checkpoints (khmerocr_cluster_ar/blockwise), usage via the netra-ocr package and the Docker app, the 1.3M-line training data, new benchmark results, limitations and licence notes. Refreshes the benchmark, architecture and example images.76c4e31
-
Upload netra-logo-transparent-new.png
Verified signature10f173d
-
Upload proposed-architecture.png
Verified signaturea7229d0 -
Upload 2 files
Verified signatureb474859
-
Upload 20 files
Verified signaturead22fff -
initial commit
Verified signature33a3e95