Model reference · open weights
MERaLiON-3-ASR is an open-weight audio or speech model from MERaLiON. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | MERaLiON |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 3.3B |
| Context | 8k tokens |
| Runs with | transformers |
| Released | 2026-05-24 |
| Popularity | 4k downloads / month |
| Licence | Commercial licence needed |
About
MERaLiON-3-ASR is the speech-recognition line in the MERaLiON-3 generation of Speech-Text Large Language Models, developed by I2R, A*STAR, Singapore. It is purpose-built for Singapore- and Southeast-Asia-centric ASR, with broad coverage across regional languages, dialects, and natural conversational code-switching.
Coverage
MERaLiON-3-ASR-API is the hosted production endpoint, tuned for real-time and enterprise transcription workloads.
On the locked evaluation suite, MERaLiON-3-ASR-API achieves the lowest mean Word Error Rate among all systems tested on English (Singapore) (12.52, vs. 25.97 / 27.34 for Gemini 3.5 Flash / GPT-4o), Cantonese (10.42, best of all systems), Hokkien (36.43, vs. 46.50 next best), and Code-switching (20.87, vs. 22.65 / 31.14). On Healthcare it is statistically tied with Gemini 3.5 Flash (20.47 vs. 20.04, within 0.5 pp).
MERaLiON-3-3B-ASR is the open-weights release published in this repository. At roughly one-third the size of its predecessor MERaLiON-2-10B-ASR, it matches or improves over the larger model on every evaluation section, with the largest gains concentrated where they matter most for the Southeast Asian setting:
| Section | MERaLiON-2-10B-ASR | MERaLiON-3-3B-ASR | Δ (pp) |
|---|---|---|---|
| Thai | 35.07 | 7.55 | −27.5 |
| Hokkien | 59.32 | 46.50 | −12.8 |
| Cantonese | 18.55 | 11.27 | −7.3 |
| Code-switching | 26.24 | 22.65 | −3.6 |
| Tamil | 28.29 | 25.83 | −2.5 |
The smaller footprint makes the open model practical for self-hosting on a single 80 GB GPU.
The figure reports mean Word Error Rate (lower is better) across twelve language and domain sections, covering 66 evaluation datasets in total. Datasets in the Healthcare and Code-switching sections also appear in their primary language section, so they contribute to both. The full per-dataset breakdown is at SEA-SpeechBench.
The table below reports per-dataset Word/Character Error Rate (lower is better) for Cantonese and Hokkien — the two regional Chinese dialects where MERaLiON-3 shows its largest relative advantage. The best result on each row is highlighted.
The four clips below illustrate cases where MERaLiON-3-ASR-API produces the most accurate transcript, MERaLiON-3-3B-ASR a near-equivalent transcript with one or two character-level differences, and a leading general-purpose model produces a substantially less faithful transcript.
The code-switching section aggregates 13 datasets of natural Southeast Asian conversational speech, totalling 5,430 samples / 35.4 hours, in which English is mixed organically with another SEA language. Coverage by direction:
| Code-switch direction | Samples | Hours |
|---|---|---|
| EN ↔ Mandarin (incl. SEAME) | 506 | 5.3 |
| IMDA Part 4 (Singlish, EN ↔ Mandarin) | 1,000 | 7.3 |
| EN ↔ Tamil | 2,184 | 9.0 |
| EN ↔ Cantonese | 904 | 6.2 |
| EN ↔ Hokkien | 536 | 3.7 |
| EN ↔ Malay | 200 | 2.6 |
| EN ↔ Vietnamese | 100 | 1.3 |
The benchmark is intended to capture real-world SEA usage patterns rather than synthetic alternation between scripts. Of the constituent corpora, only IMDA Part 4 (NSC) is publicly available; the remaining datasets are proprietary or curated in-house. Per-sample normalisation and scoring scripts for the whole evaluation are available at SEA-SpeechBench.
| Property | Value |
|---|---|
| Audio format | Mono, 16,000 Hz |
| Parameters | 3 B |
| Precision | BF16 |
| Supported languages | English (Global + Singapore), Mandarin, Malay, Tamil, Indonesian, Thai, Vietnamese, Cantonese, Hokkien |
| Supported backend | vLLM |
The model is trained as an ASR-optimised fine-tune over a multilingual mixture of curated Southeast Asian speech data, with particular emphasis on Singapore English, regional dialects (Cantonese, Hokkien), and natural English-X code-switching.
The recommended way to run MERaLiON-3-3B-ASR is through the meralion-3-asr Python package, which wraps a vLLM backend tuned for this model. Install from PyPI:
pip install meralion-3-asr
The package pre-wires the transcription prompt, decoding configuration, no-repeat-ngram guard, and 30 s audio chunking — on both the offline path and the served path. Callers only provide audio.
from meralion_3_asr import Meralion3ASR
model = Meralion3ASR.from_pretrained("MERaLiON/MERaLiON-3-3B-ASR", backend="vllm")
text = model.transcribe("audio.wav") # str
texts = model.transcribe_batch(["a.wav", "b.wav", "c.wav"]) # List[str]
Inputs may be local file paths, https:// URLs, base64 data URLs, or (numpy_array, sample_rate) tuples. Audio is automatically resampled to mono 16 kHz; long files are chunked transparently.
meralion-3-asr serve starts a FastAPI sidecar fronting an internal vllm serve process. The sidecar exposes a single OpenAI-
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys meralion-3-asr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (meralion-3-asr below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="meralion-3-asr" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.