speech recognition
FT-whisper (IDSV)
Whisper fine-tuned on the Indonesian IDSV dataset in the ITB/UI/JAIST/NAIST study.
Levelmodel
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released11 Oct 2024
Opennessunknown
Runs onnot in the notes
Statusactive
Benchmark Results
independent
IDSV (Indonesian Speech Variability)Southeast Asian and Indonesian
IDSV group SICindependent
29.64
02040
Score in WER. Lower is better.
Table 3, by speech variability
IDSV group SFMindependent
15.98
02040
Score in WER. Lower is better.
Table 3, by speech variability
IDSV test, all groupsindependent
14.85
02040
Score in WER. Lower is better.
Table 3
IDSV group RFMindependent
13.12
02040
Score in WER. Lower is better.
Table 3, by speech variability
IDSV group SIMindependent
13.04
02040
Score in WER. Lower is better.
Table 3, by speech variability
IDSV group RFCindependent
10.38
02040
Score in WER. Lower is better.
Table 3, by speech variability
IDSV test, all groupsindependent
5.44
0714
Score in CER. Lower is better.
Table 3
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
Whisper is the parent (finetune)medium confidencenotesWhere 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.
Identity
- Developer
- Institut Teknologi Bandung (ITB), Universitas Indonesia, JAIST, NAIST
- Family
- not in the notes
- Released
- 11 Oct 2024 sourcesannouncement page
- 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
- autoregressive
- 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
- IDSV Indonesian speech-variability test set, all groups (fine-tuned whisper-small): 14.85, run by paper authors (arXiv 2410.08828) arxiv.org
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Indonesian
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.
Links
DevelopersInstitut Teknologi Bandung (ITB)university, Indonesia
Universitas Indonesiauniversity, Indonesia
JAISTuniversity, Japan
NAISTuniversity, Japan
Institut Teknologi Bandung (ITB)university, IndonesiaUniversitas Indonesiauniversity, IndonesiaJAISTuniversity, JapanNAISTuniversity, JapanModelFT-whisper (IDSV)Institut Teknologi Bandung (ITB), speech recognition
FT-whisper (IDSV)Institut Teknologi Bandung (ITB), speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Organisations 4
Sources
- 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, "FT-Whisper (IDSV)", https://aurion.semai.id/models/idsv-ft-whisper/, records of October 2026.