---
language: 
- multilingual
tags:
- asr
- speech
- onnx
- onnxruntime
- quantization
- 4-bit
- ghost-assistant
- android-ai
license: apache-2.0
base_model: bezzam/omniasr-ctc-300m-v2
model_creator: Edison dos Santos
---

# OmniASR v2 (300M) - Optimized 4-bit ONNX

This repository contains the **first standalone, 4-bit quantized version** of Meta's OmniASR v2, specifically optimized for local mobile inference.

## Key Improvements by Edison dos Santos:
- **Zero Dependencies:** Unlike other distributions, this model does NOT require specialized ASR libraries. It runs on pure `onnxruntime`.
- **Mobile Optimized:** The 4-bit quantization targets the `MatMul` and `Transformer` layers with a block size of 32, tailored for ARM-based chipsets (tested on Dimensity 6300).

## Usage
Run inference_example.py (make sure to have an audio.wav file). Check the Ghost Assistant's [Technical Report](https://github.com/Edison2ST/GhostAssistantONNXFiles/blob/main/Technical%20Report.pdf) for more info and benchmarks.