Metadata-Version: 2.4
Name: pyhermeneus
Version: 0.0.1
Project-URL: Documentation, https://github.com/bernard035/hermeneus#readme
Project-URL: Issues, https://github.com/bernard035/hermeneus/issues
Project-URL: Source, https://github.com/bernard035/hermeneus
Author-email: bernard jiang <bernardjiang5@outlook.com>
License-Expression: MIT
License-File: LICENSE.txt
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.8
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: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Requires-Python: >=3.11
Description-Content-Type: text/markdown

# Hermeneus: Intelligent Voice-to-Notes System

> **Listen to Speech, Understand Meaning, Generate Insight**

`Hermeneus` is an intelligent voice processing system powered by state-of-the-art speech recognition and large language models (LLM). It enables users to upload audio recordings, automatically transcribe them into text, and leverage LLMs to deeply understand semantics—transforming spoken words into structured, actionable smart notes, summaries, action items, or knowledge cards.

Whether it's meetings, lectures, interviews, or spontaneous ideas, Hermeneus turns your voice into valuable knowledge assets, dramatically enhancing information processing and personal knowledge management.

## Name Origin: Hermeneus — The Interpreter of Meaning

The name **"Hermeneus"** draws from **Hermes**, the messenger of the Greek gods—deity of communication, language, interpretation, wisdom, and technology. Hermes did not merely deliver messages; he **interpreted** their meaning, bridging gods and mortals.

In philosophy, the term *hermeneutics*—the theory and practice of interpretation—derives from Hermes. This is precisely the mission of our system:  
**To go beyond transcription, and toward true understanding.**

`Hermeneus` embodies:

- 🗣️ **The Bridge of Communication**: Connecting human speech with digital comprehension.  
- 🔍 **The Interpreter**: Extracting insight, context, and meaning from raw audio.  
- ⚡ **The Empowerer**: Harnessing the modern "fire" of AI—Whisper and LLMs—to transform voice into structured knowledge.

We believe intelligence lies not just in recognition, but in interpretation. `Hermeneus` is that principle in action: your voice’s wise interpreter.

---

## Core Features

- ✅ **High-Accuracy Speech-to-Text**: Powered by Whisper, supporting multiple languages and audio formats.  
- ✅ **Semantic Understanding & Summarization**: Leverages LLMs to generate concise summaries and key insights.  
- ✅ **Smart Note Generation**: Converts speech into structured Markdown notes, to-dos, or knowledge cards.  
- ✅ **Context-Aware Processing**: Adapts to diverse scenarios—conversations, lectures, monologues.  
- ✅ **API-First Design**: Clean, developer-friendly API for easy integration.

## Tech Stack

- 🎤 **Speech Recognition**: OpenAI Whisper  
- 🧠 **Language Understanding & Generation**: Large Language Models (e.g., GPT, Claude, Llama)  
- 🐍 **Backend**: Python (FastAPI / Flask)  
- 📦 **Deployment**: Docker, cloud-ready (AWS/GCP/Azure)

---

> 🚀 **Begin your journey of vocal intelligence** — Upload a voice note, and let `Hermeneus` interpret the world for you.


## Table of Contents

- [Installation](#installation)
- [License](#license)

## Installation

```console
pip install hermeneus
```

## License

`hermeneus` is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.
