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.
Figures & tables
Figure 1: Polyglot-Lion achieves near-SOTA accuracy at a fraction of the model size and inference cost. Left: Average error rate (WER/CER) across 12 benchmarks; lower is better. Right: Inference speed in seconds per sample; lower is better. Despite having 6 × fewer parameters than MERaLiON-2-10B-ASR, Polyglot-Lion-1.7B matches its accuracy while being approximately 20 × faster at inference.
Lang.
Dataset
Train
Valid
Test
Total
S
H
S
H
S
H
S
H
English
Librispeech
28,539
100.59
2,700
5.36
2,619
5.39
33,858
111.34
NSC
100,000
147.97
2,997
4.90
3,000
4.95
105,997
157.82
Mandarin
AISHELL-1
120,098
150.85
14,326
18.09
7,176
10.03
141,600
178.97
AISHELL-3
56,936
56.86
6,326
6.31
24,773
22.45
88,035
85.62
Fleurs
3,246
9.73
409
1.27
945
3.07
4,600
14.07
Table 1: Dataset statistics by language, split, and duration (S = number of samples, H = hours). Full dataset descriptions, download links, and licence information are provided in Appendix A .
Model
Params
English
Mandarin (CER)
Tamil (WER)
Malay
Avg
LS
NSC
CV
AISH1
AISH3
Fleurs
CV
SLR65
SLR127
Fleurs
Meso.
Fleurs
Whisper-large-v3-turbo
0.8B
3.04
32.02
17.91
9.64
16.81
10.63
74.50
58.13
69.56
66.90
28.47
8.88
33.04
SeaLLMs-Audio-7B
7B
94.74
9.53
8.68
9.65
9.76
37.09
126.70
127.24
138.65
105.31
71.34
26.25
63.75
Qwen2.5-Omni-3B
3B
29.21
34.79
46.36
28.25
44.55
54.74
318.36
465.58
448.82
311.67
211.90
74.69
172.37
Qwen2.5-Omni-7B
7B
13.80
22.96
14.49
7.33
22.58
16.68
252.06
239.15
303.96
326.43
158.06
43.92
118.45
Qwen3-ASR-0.6B
0.6B
2.74
7.64
10.06
2.08
2.59
9.75
121.10
127.00
129.12
130.09
47.29
18.71
50.68
Table 2: ASR evaluation results. WER (%) for English, Tamil, and Malay; CER (%) for Mandarin. Lower is better. Bold = best overall; underline = second best. Rows shaded in blue are our proposed models. Dashes indicate results excluded from the average due to anomalously high error rates (WER > 200%) that would distort cross-system comparison.
Model
Time (s/sample)
MERaLiON-2-10B-ASR
2.0152 ± 0.8846
Qwen2.5-Omni-3B
1.7838 ± 1.0431
Qwen2.5-Omni-7B
1.3414 ± 0.6572
SeaLLMs-Audio-7B
0.6422 ± 0.0000
Whisper-large-v3-turbo
0.2822 ± 0.0230
Qwen3-ASR-1.7B
0.0809 ± 0.0290
Table 3: Inference latency (seconds per sample, mean ± std) measured on a single NVIDIA RTX PRO 4500 GPU. Our models are shaded in blue .
MERaLiON-2-10B
Polyglot-Lion
Training Data (Hours)
120,000
782.99
Hardware
128 × H100
1 × RTX PRO 6000
Training Time
48 h
48 h
Est. Cost
$18,862
$81
Table 4: Training resource and cost comparison. GPU rental prices sourced from RunPod.io.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Language
Dataset
Source
Description
License
English
LibriSpeech ( Panayotov et al., 2015 )
OpenSLR
English read speech derived from LibriVox public-domain audiobooks.
CC BY 4.0
NSC † (National Speech Corpus)
IMDA
Singapore English speech corpus covering multiple speaking styles (read, conversational, scripted).
Singapore Open Data Licence
Mandarin
AISHELL-1 ( Bu et al., 2017 )
OpenSLR
Mandarin read speech recorded by 400 speakers; ∼ 178 hours.
Apache 2.0
AISHELL-3 ( Shi et al., 2021 )
OpenSLR
Multi-speaker Mandarin TTS corpus ( ∼ 85 hours, 218 speakers) used here as ASR training data.
Apache 2.0
FLEURS ( Conneau et al., 2023 )
Google
Few-shot Learning Evaluation of Universal Representations of Speech; 102-language parallel benchmark.
CC BY 4.0
Common Voice 23
Mozilla
Multilingual crowdsourced speech; Mandarin subset from Mozilla Common Voice release 23.