DKSplit – Fast Word Segmentation for Python
DKSplit is a Python library for fast word segmentation. Ideal for identifying brands and extracting keywords.
DKSplit is a Python library designed for fast segmentation of web-style concatenated strings. The 9 MB ONNX model operates solely on CPU and requires Python 3.8 or higher. Users can leverage this tool to identify brands, extract keywords, and normalize identifiers. The latest version has fixed discrepancies between the split_batch() and split() functions, ensuring consistent results.