Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts

TL;DR

This paper introduces Cadence, a multilingual punctuation restoration model based on pretrained language models, which significantly improves accuracy across 22 Indian languages and English, especially in spontaneous speech transcripts, enhancing downstream NLP tasks.

Contribution

The paper presents Cadence, a novel multilingual punctuation restoration model that outperforms previous methods and supports all 22 Indian languages plus English, handling both written and spoken text effectively.

Findings

Cadence surpasses previous state-of-the-art performance in punctuation restoration.

The model effectively handles spontaneous speech transcripts with disfluencies.

Persistent challenges remain under domain shift and with rare punctuation marks.

Abstract

Punctuation plays a vital role in structuring meaning, yet current models often struggle to restore it accurately in transcripts of spontaneous speech, especially in the presence of disfluencies such as false starts and backtracking. These limitations hinder the performance of downstream tasks like translation, text to speech, summarization, etc. where sentence boundaries are critical for preserving quality. In this work, we introduce Cadence, a generalist punctuation restoration model adapted from a pretrained large language model. Cadence is designed to handle both clean written text and highly spontaneous spoken transcripts. It surpasses the previous state of the art in performance while expanding support from 14 to all 22 Indian languages and English. We conduct a comprehensive analysis of model behavior across punctuation types and language families, identifying persistent challenges under domain shift and with rare punctuation marks. Our findings demonstrate the efficacy of utilizing pretrained language models for multilingual punctuation restoration and highlight Cadence practical value for low resource NLP pipelines at scale.