speech recognitionfamily
Whisper
OpenAI multilingual ASR family; root of many fine-tunes and included in the FunASR model zoo.
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Benchmark Results
maintainer-runindependent
7.75
02040
Score in WER. Lower is better.
IDSV (Indonesian Speech Variability)Southeast Asian and Indonesian
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
3 members have no release date in the notes, so they are not on this timeline.
FT-whisper (IDSV) is a child (finetune)medium confidencenotesWhisper large-v3-turbo belongs to this familyspeech recognition2024809M
faster-whisper-small belongs to this familyspeech recognition23 Nov 2023faster-whisper-tiny belongs to this familyspeech recognition23 Nov 2023Whisper large-v3 belongs to this familyspeech recognition20231.55Bwhisper-large-v2 belongs to this familyspeech recognition5 Dec 20221.54Bwhisper-base belongs to this familyspeech recognition26 Sep 202272.59Mwhisper-medium belongs to this familyspeech recognition26 Sep 2022763.86Mwhisper-small belongs to this familyspeech recognition26 Sep 2022whisper-tiny belongs to this familyspeech recognitionWhere 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
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 Transformer encoder-decoder
- 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
- MIT License 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
- not in the notes
- Jakarta hosting
- unknown
- Languages
- 99+ languages
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
DeveloperOpenAIfrontier lab, USA
OpenAIfrontier lab, USAModelWhisperOpenAI, speech recognition
WhisperOpenAI, speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Models 10
Whisper large-v3OpenAI, speech recognitionFamilyFT-whisper (IDSV)Institut Teknologi Bandung (ITB), Universitas Indonesia, JAIST, NAIST, speech recognitionfinetunefaster-whisper-smallSYSTRAN, speech recognitionFamilyfaster-whisper-tinySYSTRAN, speech recognitionFamilyWhisper large-v3-turboOpenAI, speech recognitionFamilywhisper-smallOpenAI, speech recognitionFamilywhisper-tinyOpenAI, speech recognitionFamilywhisper-baseOpenAI, speech recognitionFamilywhisper-large-v2OpenAI, speech recognitionFamilywhisper-mediumOpenAI, speech recognitionFamilyOrganisations 1
Sources
- Gladia - Best open-source speech-to-text models in 2026 gladia.io https://www.gladia.io/blog/best-open-source-speech-to-text-models
- GitHub - modelscope/FunASR: Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diariza github.com https://github.com/modelscope/FunASR
- 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, "Whisper", https://aurion.semai.id/models/openai-whisper/, records of October 2026.