https://github.com/sippy/Infernos
Real-time multi-modal inference server for interacting with humans and other intelligences around
https://github.com/sippy/Infernos
Last synced: 17 days ago
JSON representation
Real-time multi-modal inference server for interacting with humans and other intelligences around
- Host: GitHub
- URL: https://github.com/sippy/Infernos
- Owner: sippy
- License: bsd-2-clause
- Created: 2023-09-10T15:07:35.000Z (almost 3 years ago)
- Default Branch: master
- Last Pushed: 2025-10-02T22:42:57.000Z (9 months ago)
- Last Synced: 2026-02-05T02:21:02.782Z (5 months ago)
- Language: Python
- Size: 313 KB
- Stars: 20
- Watchers: 7
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-telco - Infernos - 10]` - Real-time multi-modal inference server for interacting with humans and other intelligences around (AI & Machine Learning / Datasets & Benchmarks)
README
# I.N.F.E.R.N.O.S.
### Interactive Neural Framework for Efficient Realtime Network Operations on Streams
🔥 Welcome to Infernos, where data comes to life in real-time! 🔥
## Overview
Harness the power of **I.N.F.E.R.N.O.S.** to transform audio, video, and
text streams with state-of-the-art inference in an instant. Embrace a
blazing-fast future, free from lag.
## News
Initial integration of the LLM (Qwen 2.5) and addition of the A.I.
Attendant application.
Upcoming presentation at the OpenSIPS Summit 2025.
## Features
- **Interactive:** Infernos isn't just another tool; it's an
experience. Speak in one voice and marvel as it's automatically
translated into a completely different tone or even language, and
then seamlessly transmitted in real-time during phone or web
meetings.
- **Neural Power:** With deep learning at its core, Infernos is
optimized for top-notch performance.
- **Multimodal Support:** Whether it's audio, video, or text, Infernos
handles them with elegance.
- **Efficiency:** Designed for low-latency, high-throughput
operations.
- **Realtime:** Don't wait. Experience the magic as it unfolds.
## Quick Start
1. Clone the repository:
```bash
git clone https://github.com/sippy/Infernos.git
```
2. Navigate to the project directory and install dependencies:
```bash
cd Infernos && pip install -r requirements.txt
```
3. Create a configuration file. In the following example we would
listen and accept SIP calls from `MY_IP` and pass them into Live
Translator application. Then use SIP account to send
outbound call legs to `DEST_NUM`@`MY_SIP_SRV`:
```bash
MY_IP="A.B.C.D"
MY_SIP_SRV="E.F.G.H"
DEST_NUM="12345"
DEST_USER="foo"
DEST_PWD="bar"
cat > config.yaml <English / English->Portugese
on a AWS instance "from zero to hero" in less than 60 minutes.
- [Infernos: cost efficient AI inference for real-time applications:](https://www.youtube.com/watch?v=eawO0hXeO5Y)
Overview of the Infernos architecture and progress over the past few months.
## Join US
- [Discord](https://discord.gg/bb95ZWhrhQ)
------------------------------------------------------------------------
Stay on the lookout for more sizzling updates, and always remember:
**Infernos** makes the future sizzle!