Project AURIONAI Use-Cases Research & Innovation
speech recognitionfamily

MMS

Multilingual speech model lineage; Omnilingual ASR descends from it; fine-tuned for Indonesian in the IDSV study.

MetaMetaUSA
Meta
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessunknown
Runs onnot in the notes
Statusactive

Benchmark Results

independent
IDSV (Indonesian Speech Variability)Southeast Asian and Indonesian
mms-1b-allIDSV test, all, zero-shotindependent
9.57
0714

Score in CER. Lower is better.

Table 3Oct 2024 arxiv.org
mms-1b-allIDSV test, all, zero-shotindependent
29.3
02040

Score in WER. Lower is better.

Table 3Oct 2024 arxiv.org
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

finetunesuccessor
MMS to MMS fine-tuned with LM (IDSV): finetune, medium confidenceMMS to MMS fine-tuned, no LM (IDSV): finetune, medium confidenceMMS to Omnilingual ASR: successor, medium confidencewav2vec 2.0 to Omnilingual ASR: successor, medium confidenceMMSMMSMetawav2vec 2.0wav2vec 2.0MetaMMS fine-tuned with LM (IDSV)MMS fine-tuned with LM (ID…Institut Teknologi Bandung (ITB),…MMS fine-tuned, no LM (IDSV)MMS fine-tuned, no LM (IDS…Institut Teknologi Bandung (ITB),…Omnilingual ASROmnilingual ASRMeta, Nov 2025
Institut Teknologi Bandung (ITB)MMS fine-tuned with LM (IDSV) is a child (finetune)medium confidencenotes
Institut Teknologi Bandung (ITB)MMS fine-tuned, no LM (IDSV) is a child (finetune)medium confidencenotes
MetaOmnilingual ASR is a child (successor)medium confidencenotes
mms-300m-1130-forced-aligner belongs to this familyspeech recognition2 May 2024315.47M
Metamms-1b-all belongs to this familyspeech recognition27 May 2023
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 5 models. Confidence and evidence are the notes' own.

R&D Topics

Massively multilingual speech recognitionexemplarText-to-speech for low-resource languagesexemplar

Identity

Developer
Meta
Family
not in the notes
Released
– sources
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
other
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
audio
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
measured on a benchmark
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/pdf/2511.09690 https://arxiv.org/pdf/2511.09690
  2. Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities arxiv.org https://arxiv.org/html/2410.08828v2

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MMS", https://aurion.semai.id/models/meta-mms/, records of October 2026.