Downloads · 30 days
0
omniASR_CTC_300M_v2_Q4_ONNX
Edison2ST/omniASR_CTC_300M_v2_Q4_ONNX
omniASR_CTC_300M_v2_Q4_ONNX is a machine learning model from Edison2ST. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains the first standalone, 4-bit quantized version of Meta's OmniASR v2, specifically optimized for local mobile inference.
Access
Public
Updated Jan 25, 2026
Repo size
248 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx248 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jan 25, 2026
- Updated
- Jan 25, 2026
- SHA
- 3cd8cb00
Base models
Model card
From the Hugging Face model README
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
MatMulandTransformerlayers 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.
- License
- apache-2.0
- Languages
- multilingual
- Created
- Jan 25, 2026
- Updated
- Jan 25, 2026