Metadata-Version: 2.4
Name: turkman_ocr
Version: 0.1.1
Summary: Turkmen language LSTM model for Tesseract OCR — pip install turkman_ocr
Author-email: turkman-ocr <your@email.com>
License: MIT License
        
        Copyright (c) 2026 turkman-ocr
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
        
Project-URL: Homepage, https://github.com/yourusername/turkman_ocr
Project-URL: Bug Tracker, https://github.com/yourusername/turkman_ocr/issues
Keywords: ocr,tesseract,turkmen,lstm,nlp,turkmenistan
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing :: Linguistic
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: tesseract
Requires-Dist: pytesseract>=0.3.10; extra == "tesseract"
Requires-Dist: Pillow>=9.0.0; extra == "tesseract"
Dynamic: license-file

# turkman_ocr

**Turkmen language LSTM model for Tesseract OCR**

O'zbek tilida: Tesseract OCR uchun Turkman tili LSTM modeli.

## O'rnatish

```bash
pip install turkman_ocr
```

## Ishlatish

### 1. Model faylini tessdata papkasiga o'rnatish

```python
import turkman_ocr

# Avtomatik topib o'rnatadi
turkman_ocr.install()

# Yoki yo'lni o'zingiz ko'rsating:
turkman_ocr.install(tessdata_dir=r"C:\Program Files\Tesseract-OCR\tessdata")
```

### 2. Model faylining yo'lini olish

```python
import turkman_ocr

path = turkman_ocr.get_model_path()
print(path)  # .../site-packages/turkman_ocr/data/turkman_ocr.lstm
```

### 3. Package ma'lumotlari

```python
import turkman_ocr
import pprint

pprint.pprint(turkman_ocr.info())
# {
#   'package': 'turkman_ocr',
#   'version': '0.1.0',
#   'model_size_mb': 3.12,
#   'language': 'Turkmen (tuk)',
#   'engine': 'Tesseract LSTM',
#   'tessdata_dir': 'C:\\Program Files\\Tesseract-OCR\\tessdata',
#   'model_installed': True,
#   ...
# }
```

### 4. Tesseract bilan OCR qilish

```python
import turkman_ocr
import pytesseract
from PIL import Image

# Avval o'rnating
turkman_ocr.install()

# Keyin ishlatish
img = Image.open("rasm.png")
text = pytesseract.image_to_string(img, lang="turkman_ocr")
print(text)
```

### 5. O'chirish

```python
import turkman_ocr
turkman_ocr.uninstall()
```

## Talablar

- Python 3.7+
- [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) o'rnatilgan bo'lishi kerak

## Litsenziya

MIT License
