Modelpublic

Abddar/muaalem-v3-2-int8-android-onnx

sourceHugging Facemitupdated 1mo agoView on Hugging Face

0likes

Model Card

Quran Muaalem v3.2 — Android INT8 ONNX

This repository hosts the Android-ready single-file INT8 ONNX artifact used by the azani_w_qiblati offline Quran recitation and tajweed feedback feature.

Provenance

—Upstream model: `obadx/muaalem-model-v3_2`
—Pinned upstream revision: 01a1ef9fbe40d144ef845101e89ff924aed3fef5
—Upstream project: `obadx/quran-muaalem`
—License: MIT

The source artifact was already dynamically quantized to INT8. This Android package only embeds the external ONNX initializer data into one .onnx file:

text

onnx.load(load_external_data=True)
  + convert_model_from_external_data
  + onnx.save_model(save_as_external_data=False)

It was not requantized or graph-optimized. The mathematical graph is unchanged.

Artifact integrity

File	Size	SHA-256
`muaalem_tajweed_int8.onnx`	`876,466,434` bytes	`3ef7f9760b54161d876b5866fccd19cbcc7b793386753f515395f2d5012e9f96`

The consuming application verifies both the exact byte count and SHA-256 before promoting a completed download. Interrupted downloads can resume using HTTP Range requests.

Intended use

This artifact is intended for on-device ONNX Runtime inference on Android. It does not include a hosted inference API. The surrounding application supplies the pinned preprocessing, vocabularies, decoding, Quran reference text, and tajweed feedback logic.

Attribution

All model credit belongs to the Quran Muaalem authors and contributors. This repository provides a deployment-oriented repackaging of their MIT-licensed model for offline Android use.