Metadata-Version: 2.4
Name: latin-itn
Version: 0.1.0
Summary: Inverse Text Normalization (Casing & Punctuation Restoration) for Classical Latin ASR.
Author-email: Nathan Anderson <nateandero@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/njand/latin-itn
Project-URL: Bug Tracker, https://github.com/njand/latin-itn/issues
Project-URL: HuggingFace Model, https://huggingface.co/njand/latin-asr-postprocessor
Project-URL: Training Repo, https://github.com/njand/latin-asr-postprocess
Keywords: latin,nlp,asr,itn,casing-restoration,punctuation-restoration,transformers
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: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.0.0
Requires-Dist: transformers>=4.30.0
Dynamic: license-file

# Latin ITN (`latin-itn`)

Inverse Text Normalization (Casing & Trailing Punctuation Restoration) for Latin ASR transcriptions.

## Installation

```bash
pip install latin-itn

```

## Quickstart

```python
from latin_itn import LatinITNPredictor

predictor = LatinITNPredictor.from_pretrained("njand/latin-asr-postprocessor")

raw_text = "gallia est omnis divisa in partes tres quarum unam incolunt belgae"
formatted_text = predictor.predict(raw_text)

print(formatted_text)
# Output: "Gallia est omnis divisa in partes tres, quarum unam incolunt Belgae."

```
