Metadata-Version: 2.4
Name: eng-to-ru-transcriber
Version: 0.2.0
Summary: automatic English-to-Cyrillic text transcriber
Author: kodovy-pesets
License: MIT
Project-URL: Homepage, https://github.com/Isyarname/eng-to-ru-transcriber
Project-URL: Repository, https://github.com/Isyarname/eng-to-ru-transcriber
Project-URL: Issues, https://github.com/Isyarname/eng-to-ru-transcriber/issues
Keywords: transliteration,phonetics,english,russian,ipa,g2p
Classifier: Development Status :: 3 - Alpha
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Natural Language :: English
Classifier: Natural Language :: Russian
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: gruut>=2.4.0
Requires-Dist: platformdirs>=4.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Dynamic: license-file

# English-to-Russian Phonetic Transcriber 🔤

[Читать на русском языке](https://github.com/Isyarname/eng-to-ru-transcriber/blob/main/README.ru.md)

A Python library for automatic English-to-Cyrillic text transcription using a hybrid engine: dictionary lookup and neural G2P (`gruut`) for unknown words.

## 💡 Features

- **Universal transcription** — handles any English text, including invented words, neologisms, and rare names.
- **Custom vocabulary** — augment the built-in dictionary with your own overrides.

## ⚡ Key Highlights

- **Two-tier lookup** — IPA via local 120k+ dict + neural G2P backup.
- **Graphemic adaptation** — Cyrillic matches Russian orthography.

## 🚀 Installation

```bash
pip install eng-to-ru-transcriber
```

## 💻 Usage

### Basic Example

```python
from eng_to_ru_transcriber import Transcriber

t = Transcriber()
print(t.transcribe("Hello world"))
# → Хэлоу уорлд
```

### Custom Vocabulary

```python
from eng_to_ru_transcriber import Transcriber

custom_vocabulary = {"python": "ˈpaɪθɑn"}
t = Transcriber(custom_vocabulary=custom_vocabulary)
print(t.transcribe("Python is great"))
```

## 🧪 Testing

```bash
pip install pytest
pytest
```

## 📊 Data Sources

Based on curated IPA data from OpenWiktionary.

## 📜 License

MIT
