Metadata-Version: 2.4
Name: olaverse
Version: 0.1.3
Summary: Advanced ML infrastructure and interface to load and run all Olaverse models
Author-email: Olaverse <support@olaverse.co.uk>
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.20.0
Requires-Dist: requests>=2.25.0
Requires-Dist: tqdm>=4.50.0
Requires-Dist: tokenizers>=0.13.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: jupyter>=1.0.0; extra == "dev"
Requires-Dist: scikit-learn>=1.0.0; extra == "dev"
Provides-Extra: docs
Requires-Dist: mkdocs-material; extra == "docs"
Requires-Dist: mkdocstrings[python]; extra == "docs"
Provides-Extra: legal
Requires-Dist: unsloth; extra == "legal"
Provides-Extra: deeplearning
Requires-Dist: torch; extra == "deeplearning"
Requires-Dist: transformers; extra == "deeplearning"
Dynamic: license-file

# Olaverse Documentation

[![PyPI Version](https://img.shields.io/badge/pypi-v0.1.2-blue)](https://pypi.org/)
[![License](https://img.shields.io/badge/license-Apache%202.0-green)](LICENSE)
[![Platform](https://img.shields.io/badge/platform-CPU%20&%20GPU-orange)](https://github.com/)
[![Docs](https://img.shields.io/badge/docs-GitHub_Pages-blue)](https://Olaverse-Labs.github.io/olaverse/)

Welcome to the official developer documentation for the **Olaverse SDK**.

**Olaverse** is a unified Python package and developer interface designed to seamlessly integrate state-of-the-art African NLP features, Text-to-Speech (TTS) architecture, and Large Language Models (LLMs) into your applications.

**📚 Full API Documentation is available at [https://Olaverse-Labs.github.io/olaverse/](https://Olaverse-Labs.github.io/olaverse/)**

---

## Key Capabilities

- **🗣️ Natural Language Processing**: Accurate text diacritization (Yoruba, Igbo), Language Detection (covering 5 local languages), custom Byte-Level BPE tokenization, and robust PII masking.
- **🎙️ Speech Synthesis**: End-to-End Text-to-Speech (TTS) pipelines to translate normalized text and restored tones into high-fidelity audio waveforms.
- **🧠 Large Language Models**: Easy, memory-efficient inference interfaces for loading advanced domain-specific LLMs (like `LegalPeace` for legal contract reasoning).
- **🌍 Global Utilities**: Built-in constants, universal currency formatters, and generic `.wav` audio I/O tools.

---

## Quick Install

```bash
pip install olaverse
```

---

## Navigation

- **[NLP & Tokenization](https://Olaverse-Labs.github.io/olaverse/nlp/)**: Explore the `Tokenizer`, Language Detection, Diacritization, and PII masking tools.
- **[Speech Synthesis](https://Olaverse-Labs.github.io/olaverse/speech/)**: Learn how to use the End-to-End `TTSPipeline` and extend it with custom Acoustic models.
- **[Language Models](https://Olaverse-Labs.github.io/olaverse/llm/)**: Explore how to run large models like `LegalPeace` and the Neural language detector.
- **[Global Utilities](https://Olaverse-Labs.github.io/olaverse/utils/)**: Check out the built-in generic constants and audio utilities.
