Edison2ST/omniASR_CTC_300M_v2_Q4_ONNX

By Edison2ST · ↓ 0 · ♥ 2 · Updated 2026-01-25

What's in this repo

This page lists the files in Edison2ST/omniASR_CTC_300M_v2_Q4_ONNX, including omni_v2_q4.onnx.

1 ONNX models (.onnx files)
9 files, including 3 .py, 1 .md, 1 .onnx, 1 .json
Last updated 2026-01-25

ONNX files

File	Size	Download
omni_v2_q4.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

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 for more info and benchmarks.

Model info

onnx asr speech onnxruntime quantization 4-bit ghost-assistant android-ai multilingual base_model:bezzam/omniasr-ctc-300m-v2 base_model:quantized:bezzam/omniasr-ctc-300m-v2 license:apache-2.0

↓ 0 ♥ 2

Created: 2026-01-25

Updated: 2026-01-25

View on Hugging Face

Files (9)

.gitattributes

LICENSE

NOTICE

README.md

generate_vocab.py

inference_example.py

omniQ4.py

omni_v2_q4.onnx ONNX

vocab.json

Related models

More models

No task type declared.