olaverse 0.1.4

Advanced ML infrastructure and interface to load and run all Olaverse models

Olaverse Documentation

Welcome to the official developer documentation for the Olaverse SDK.

Olaverse is a unified Python package and developer interface for African NLP, Large Language Models, and Text-to-Speech architecture.

📚 Full API Documentation: https://Olaverse-Labs.github.io/olaverse/

---

Key Capabilities

• 🗣️ Natural Language Processing: Diacritization (Yoruba, Igbo), Language Detection for 5 Nigerian languages (lightweight LIDLite5 and neural LIDNeural5), Byte-Level BPE tokenization, PII masking, and TTS text normalization.
• ⚡ MIST Model Family: Unified interface for the MIST LLM family (8B, 70B, 140B, Thinking). Supports local inference via transformers and hosted inference via Featherless or any OpenAI-compatible endpoint. Correct stop tokens and generation defaults per variant are baked in.
• 🧠 Domain LLMs: LegalPeace — memory-efficient 4-bit inference for legal contract reasoning (fine-tuned Mistral-7B-v0.3).
• 🎙️ Speech Architecture (Roadmap / Experimental): TTS pipeline architecture connecting normalization, diacritization, acoustic model, and vocoder. The NLP front-end is production-ready; acoustic synthesis is in development.
• 🌍 Global Utilities: Nigerian currency formatters, generic constants, and .wav audio I/O tools.

---

Quick Install

# Core (NLP, tokenizer, lightweight LID)
pip install olaverse

# Neural models (LIDNeural5, MIST local inference)
pip install olaverse[deeplearning]

# Hosted inference (MIST via Featherless, Modal, etc.)
pip install olaverse[hosted]

# Legal reasoning (LegalPeace)
pip install olaverse[legal]

---

Navigation

• NLP & Tokenization: Tokenizer, Language Detection, Diacritization, PII masking, TTS normalizer.
• Language Models: MIST model family, LegalPeace, LIDNeural5.
• Speech Architecture: TTSPipeline and base classes (experimental — roadmap).
• Global Utilities: Constants and audio utilities.