Project AURIONAI Use-Cases Research & Innovation
speech recognition

wav2vec2-indonesian-javanese-sundanese

A speech recognition model for Indonesian, Javanese and Sundanese from the Multilingual Speech Recognition for Indonesian Languages project, fine-tuned from wav2vec2-large-xlsr-53.

Indonesian NLPIndonesian NLP
Indonesian NLP
Levelmodel
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released2 Mar 2022
Opennessopen weights permissive
Runs onnot in the notes
Statusnot in the notes

Benchmark Results

vendor-reported
Common Voice 6.1 6.1speech
Indonesian test split; CER 1.472vendor-reported
4.056
02.55

Score in WER. Lower is better.

huggingface.co
Common Voice 7 7.0speech
Indonesian test split; CER 1.577vendor-reported
4.492
02.55

Score in WER. Lower is better.

huggingface.co
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

finetune
wav2vec2-large-xlsr-53 to wav2vec2-indonesian-javanese-sundanese: finetune, high confidencewav2vec2-large-xlsr-53wav2vec2-large-xlsr-53Metawav2vec2-indonesian-javanese-sundanesewav2vec2-indonesian-javane…Indonesian NLP, Mar 2022
Metawav2vec2-large-xlsr-53 is the parent (finetune)high confidencemodel card
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, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Speech recognition for Indonesian and regional languagesexemplarLow-resource and regional language resourcesproduced by

Identity

Developer
Indonesian NLP
Family
not in the notes
Released
2 Mar 2022 sourcesregistry date
Weights published
2 Mar 2022
Record checked
11 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 wav2vec2-large-xlsr-53 fine-tuned with CTC
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
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
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
Javanese, Sundanese
Jakarta hosting
unknown
Languages
Indonesian (Common Voice), Javanese (OpenSLR SLR41) and Sundanese (OpenSLR SLR44)
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. huggingface.co/indonesian-nlp/wav2vec2-indonesian-javanese-s... https://huggingface.co/indonesian-nlp/wav2vec2-indonesian-javanese-sundanese
  2. huggingface.co/api/models/indonesian-nlp/wav2vec2-indonesian... https://huggingface.co/api/models/indonesian-nlp/wav2vec2-indonesian-javanese-sundanese

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "wav2vec2-Indonesian-Javanese-Sundanese", https://aurion.semai.id/models/indonesian-nlp-wav2vec2-indonesian-javanese-sundanese/, records of October 2026.