Image-to-Text
Transformers
Safetensors
Turkish
English
ocr
turkish
document-intelligence
vision-language-model
svtrv2
qwen2.5-vl
kvkk
pii-redaction
legal-nlp
ictihat
financial-verification
visual-redaction
Eval Results (legacy)
Instructions to use ersanbil/TurkceOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ersanbil/TurkceOCR 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="ersanbil/TurkceOCR")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ersanbil/TurkceOCR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download turkceocr/data/__init__.py from ersanbil/TurkceOCR: direct link, hf CLI and curl.
- Browser
- Download file 1.42 kB
-
https://huggingface.co/ersanbil/TurkceOCR/resolve/main/turkceocr/data/__init__.py
- Command line
-
hf download hf://ersanbil/TurkceOCR/turkceocr/data/__init__.py
-
curl -L -o __init__.py https://huggingface.co/ersanbil/TurkceOCR/resolve/main/turkceocr/data/__init__.py
1.42 kB
| """ | |
| TürkçeOCR Veri Üretim ve Fiziksel Belge Bozulma Motoru (`TurkceDegrade`). | |
| """ | |
| from turkceocr.data.degradation import DegradationResult, TurkceDegrade | |
| from turkceocr.data.hf_loader import ( | |
| DatasetSufficiencySummary, | |
| TurkishOCRDataQualityFilter, | |
| TurkishOCRDatasetMixer, | |
| build_stamp_underneath_token_mask, | |
| ) | |
| from turkceocr.data.pdf_and_table_engine import ( | |
| BornDigitalPDFPairGenerator, | |
| ComplexTableItem, | |
| ComplexTurkishTableRenderer, | |
| ) | |
| from turkceocr.data.photometric_ops import ( | |
| attenuate_stamp_overlay, | |
| illumination_division_normalization, | |
| remove_table_grid_lines, | |
| ) | |
| from turkceocr.data.stamp_signature import ( | |
| StampMetadata, | |
| TurkishStampAndSignatureEngine, | |
| ) | |
| from turkceocr.data.synthetic_generator import ( | |
| AGGLUTINATIVE_HARD_LEXICON, | |
| SyntheticDocumentSample, | |
| TurkishDocumentGenerator, | |
| ) | |
| __all__ = [ | |
| "TurkceDegrade", | |
| "DegradationResult", | |
| "TurkishStampAndSignatureEngine", | |
| "StampMetadata", | |
| "TurkishDocumentGenerator", | |
| "SyntheticDocumentSample", | |
| "AGGLUTINATIVE_HARD_LEXICON", | |
| "TurkishOCRDatasetMixer", | |
| "TurkishOCRDataQualityFilter", | |
| "DatasetSufficiencySummary", | |
| "build_stamp_underneath_token_mask", | |
| "ComplexTurkishTableRenderer", | |
| "ComplexTableItem", | |
| "BornDigitalPDFPairGenerator", | |
| "illumination_division_normalization", | |
| "remove_table_grid_lines", | |
| "attenuate_stamp_overlay", | |
| ] | |