# Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition

arXiv: https://arxiv.org/abs/2505.17538 · HTML: https://mlsanity.com/paper/2505.17538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 7 of 7)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [LEONARDO: A Pan-European Pre-Exascale Supercomputer for HPC and AI Applications](https://mlsanity.com/paper/2307.16885/) (2023)
- [Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges](https://mlsanity.com/paper/2402.01917/) (2024)
- [Hearing voices at the National Library -- a speech corpus and acoustic model for the Swedish language](https://mlsanity.com/paper/2205.03026/) (2022)

## Abstract (arXiv)

This work presents a suite of fine-tuned Whisper models for Swedish, trained on a dataset of unprecedented size and variability for this mid-resourced language. As languages of smaller sizes are often underrepresented in multilingual training datasets, substantial improvements in performance can be achieved by fine-tuning existing multilingual models, as shown in this work. This work reports an overall improvement across model sizes compared to OpenAI's Whisper evaluated on Swedish. Most notably, we report an average 47% reduction in WER comparing our best performing model to OpenAI's whisper-large-v3, in evaluations across FLEURS, Common Voice, and NST.