Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR

• URL: http://arxiv.org/abs/2603.16184v1
• Date: Tue, 17 Mar 2026 07:09:42 GMT
• Title: Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR
• Abstract summary: We present Polyglot-Lion, a family of compact multilingual automatic speech recognition (ASR) models tailored for the linguistic landscape of Singapore.<n>Our models are obtained by fine-tuning Qwen3-ASR-0.6B and Qwen3-ASR-1.7B exclusively on publicly available speech corpora.<n>On 12 benchmarks spanning the four target languages, Polyglot-Lion-1.7B achieves an average error rate of 14.85, competitive with MERaLiON-2-10B-ASR (14.32)<n>Inference throughput is approximately 20x faster than MERaLiON at 0.10 s/sample
• Score: 1.7802147489386628
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Polyglot-Lion, a family of compact multilingual automatic speech recognition (ASR) models tailored for the linguistic landscape of Singapore, covering English, Mandarin, Tamil, and Malay. Our models are obtained by fine-tuning Qwen3-ASR-0.6B and Qwen3-ASR-1.7B exclusively on publicly available speech corpora, using a balanced sampling strategy that equalizes the number of training utterances per language and deliberately omits language-tag conditioning so that the model learns to identify languages implicitly from audio. On 12 benchmarks spanning the four target languages, Polyglot-Lion-1.7B achieves an average error rate of 14.85, competitive with MERaLiON-2-10B-ASR (14.32) - a model 6x larger - while incurring a training cost of \$81 on a single RTX PRO 6000 GPU compared to \$18,862 for the 128-GPU baseline. Inference throughput is approximately 20x faster than MERaLiON at 0.10 s/sample versus 2.02 s/sample. These results demonstrate that linguistically balanced fine-tuning of moderate-scale pretrained models can yield deployment-ready multilingual ASR at a fraction of the cost of larger specialist systems.

Related papers

• BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models [10.996463837873725]
  We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages.<n>Our models achieve state-of-the-art CER among open-source systems on 27 of 102 languages on the combined FLEURS and Common Voice test set.
  arXiv  Detail & Related papers  (2026-09-09T00:18:08Z)
• Qwen3-ASR Technical Report [71.87071808763484]
  We introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model.<n>Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects.
  arXiv  Detail & Related papers  (2026-01-29T06:58:13Z)
• Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices [1.4625828590961276]
  We present a suite of tiny automatic speech recognition (ASR) models specialized for a range of underrepresented languages.<n>We release Arabic, Chinese, Japanese, Korean, Ukrainian, and Vietnamese models under a permissive open-source license.
  arXiv  Detail & Related papers  (2025-09-02T17:22:54Z)
• Efficient Adaptation of Multilingual Models for Japanese ASR [0.0]
  This study explores fine-tuning multilingual ASR (Automatic Speech Recognition) models, specifically OpenAI's Whisper-Tiny, to improve performance in Japanese.<n>Using Japanese-specific datasets and Low-Rank Adaptation (LoRA) along with end-to-end (E2E) training, we fine-tuned Whisper-Tiny to bridge this gap.<n>Our results show that fine-tuning reduced Whisper-Tiny's Character Error Rate (CER) from 32.7 to 20.8 with LoRA and to 14.7 with end-to-end fine-tuning, surpassing Whisper-Base's CER of 20.
  arXiv  Detail & Related papers  (2024-12-14T06:32:16Z)
• Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations [59.056367787688146]
  This paper pioneers exploring and training powerful Multilingual Math Reasoning (xMR) LLMs. We construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages. By utilizing translation, we construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages.
  arXiv  Detail & Related papers  (2023-10-31T08:09:20Z)
• From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition [50.93943755401025]
  We propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses.
  arXiv  Detail & Related papers  (2023-01-19T02:37:56Z)
• Few-shot Learning with Multilingual Language Models [66.49496434282564]
  We train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages. Our largest model sets new state of the art in few-shot learning in more than 20 representative languages. We present a detailed analysis of where the model succeeds and fails, showing in particular that it enables cross-lingual in-context learning.
  arXiv  Detail & Related papers  (2021-12-20T16:52:35Z)
• XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale [48.0390317915984]
  XLS-R is a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128 languages.
  arXiv  Detail & Related papers  (2021-11-17T18:49:42Z)
• Multilingual Speech Translation with Efficient Finetuning of Pretrained Models [82.22294901727933]
  A minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual and cross-modality transfer ability. Our approach demonstrates strong zero-shot performance in a many-to-many multilingual model.
  arXiv  Detail & Related papers  (2020-10-24T08:15:08Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.