Saved in:
Bibliographic Details
Main Author: Martínez, Héctor Javier Vázquez
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.26292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918412974817280
author Martínez, Héctor Javier Vázquez
author_facet Martínez, Héctor Javier Vázquez
contents Syllable-level units offer compact and linguistically meaningful representations for spoken language modeling and unsupervised word discovery, but research on syllabification remains fragmented across disparate implementations, datasets, and evaluation protocols. We introduce findsylls, a modular, language-agnostic toolkit that unifies classical syllable detectors and end-to-end syllabifiers under a common interface for syllable segmentation, embedding extraction, and multi-granular evaluation. The toolkit implements and standardizes widely used methods (e.g., Sylber, VG-HuBERT) and allows their components to be recombined, enabling controlled comparisons of representations, algorithms, and token rates. We demonstrate findsylls on English and Spanish corpora and on new hand-annotated data from Kono, an underdocumented Central Mande language, illustrating how a single framework can support reproducible syllable-level experiments across both high-resource and under-resourced settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26292
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding
Martínez, Héctor Javier Vázquez
Computation and Language
Artificial Intelligence
Syllable-level units offer compact and linguistically meaningful representations for spoken language modeling and unsupervised word discovery, but research on syllabification remains fragmented across disparate implementations, datasets, and evaluation protocols. We introduce findsylls, a modular, language-agnostic toolkit that unifies classical syllable detectors and end-to-end syllabifiers under a common interface for syllable segmentation, embedding extraction, and multi-granular evaluation. The toolkit implements and standardizes widely used methods (e.g., Sylber, VG-HuBERT) and allows their components to be recombined, enabling controlled comparisons of representations, algorithms, and token rates. We demonstrate findsylls on English and Spanish corpora and on new hand-annotated data from Kono, an underdocumented Central Mande language, illustrating how a single framework can support reproducible syllable-level experiments across both high-resource and under-resourced settings.
title findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.26292