ABTdomain/dksplit

By ABTdomain · ↓ 0 · ♥ 1 · Updated 2026-02-11

What's in this repo

This page lists the files in ABTdomain/dksplit, including dksplit-int8.onnx.

1 ONNX models (.onnx files)
4 files, including 1 .md, 1 .onnx, 1 .npz
Last updated 2026-02-11

ONNX files

File	Size	Download
dksplit-int8.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

DKSplit

Word segmentation model for concatenated text. Split domain names, brand names, and phrases into words.

Current Version: 0.2.3

Model Description

Architecture: BiLSTM-CRF (384 embedding, 768 hidden, 3 layers)
Format: ONNX with INT8 quantization
Size: ~9MB
Input: Lowercase a-z, 0-9 (max 64 characters)

Usage

Install

pip install dksplit

Python

import dksplit

dksplit.split("chatgptlogin")
# ['chatgpt', 'login']

dksplit.split_batch(["openaikey", "microsoftoffice"])
# [['openai', 'key'], ['microsoft', 'office']]

Direct ONNX

import onnxruntime as ort
import numpy as np

session = ort.InferenceSession("dksplit-int8.onnx")
# See GitHub for full inference code

Files

dksplit-int8.onnx - ONNX model (INT8 quantized)
dksplit.npz - CRF parameters

Limitations

Input: a-z, 0-9 only
Max length: 64 characters
Non-Latin scripts: use Romanized form

License

Please attribute as: DKsplit by ABTdomain

Model info

token-classification onnx

onnx onnxruntime word-segmentation bilstm-crf text-processing domain-names token-classification en fr de es it

↓ 0 ♥ 1

Created: 2026-01-07

Updated: 2026-02-11

View on Hugging Face

Files (4)

.gitattributes

README.md

dksplit-int8.onnx ONNX

dksplit.npz

Related models

More from ABTdomain

No other models by this author.

More token-classification models

Browse all token-classification models