Project AURIONAI Use-Cases Research & Innovation
speech recognition

whisper-small

Small Whisper model evaluated zero-shot on the Indonesian IDSV test set.

OpenAIOpenAIUSAWhisperFamily
OpenAI
Levelvariant
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released26 Sep 2022
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Benchmark Results

independent
IDSV (Indonesian Speech Variability)Southeast Asian and Indonesian
IDSV test, all, zero-shotindependent
30.87
02040

Score in WER. Lower is better.

Table 3Oct 2024 arxiv.org
IDSV test, all, zero-shotindependent
13.84
0714

Score in CER. 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

quantize
whisper-small to faster-whisper-small: quantize, high confidencewhisper-smallwhisper-smallOpenAI, Sep 2022faster-whisper-smallfaster-whisper-smallSYSTRAN, Nov 2023
SYSTRANfaster-whisper-small is a child (quantize)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

Massively multilingual speech recognitionproduced by

Identity

Developer
OpenAI
Family
Whisper
Released
26 Sep 2022 sourcesregistry date
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
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
  • IDSV Indonesian speech-variability test set, all groups (whisper-small, not fine-tuned): 30.87, run by paper authors (arXiv 2410.08828) arxiv.org
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. Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities arxiv.org https://arxiv.org/html/2410.08828v2
  2. huggingface.co/openai/whisper-small https://huggingface.co/openai/whisper-small

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Whisper-Small", https://aurion.semai.id/models/openai-whisper-small/, records of October 2026.