whatmodel.sh / stt / Whisper small.en

Whisper small.en

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Whisper small.en is an open-weights speech-to-text model from OpenAI, released September 2022. Its published size is 0.244B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact checkpoint openai/whisper-small.en (openai-whisper name 'small.en'). Params from the Whisper README size table. Licence as declared on the HF card.

44.0±2.9#126 of 162 speech-to-text modelsfrom 6 benchmark results across 5 sources

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of Whisper small.en, out of 176 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
137Omnilingual ASR CTC 300M Meta45±2local~1.3GB2025-11
138Distil-Whisper distil-medium.en Hugging Face (Distil-Whisper)44±3local~1.4GB2023-10
139Whisper small.en OpenAI44±3local~1.1GB2022-09
140ESPnet Branchformer 18-layer (70 epochs, no LM) ESPnet44±4local~0.7GB2022-06
141Nemotron 3.5 ASR Streaming 0.6B NVIDIA44±3local~0.7GB2026-05
more from OpenAI
13GPT Transcribe OpenAI64±4api $0.0045/audio min2026-07
48GPT-Realtime-Whisper OpenAI59±3api $0.017/audio min2026-05
61Whisper large-v3-turbo OpenAI57±1api $0.0005/audio min +local~2.4GB2024-10

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests5 not in a task · 97% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER +13.1% ✎▁···▁▁▂·▄▄██ beats 10/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 39%blunt · several runs
Open ASR English short-form WER (March 2026)8.6% ✎▁▁▁▃··▁▁▂██▆ beats 25/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇ 29%blunt
FLEURS English test WER6.1% ✎▁··▁▁▁▁▁▁▃█▁ beats 16/56avg 5.8%▇▇▇▇▇▇ 15%blunt
Picovoice STT benchmark · English batch 4-set mean WER7.0% ✎▄···▄···▄··█ beats 2/4avg 5.7%▇▇▇ 8.5%blunt
AfriSpeech-200 test (108 African accents) · WER41.4% ✎███····█████ beats 3/7avg 30%▇▇ 4.7%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~1.09 GB · from github.com/openai (official)
    uvx --from openai-whisper whisper audio.mp3 --model small.en

Official weights and documentation: huggingface.co/openai ↗

$ how the score was worked out · transcribe.cpp model catalog… 52%, Open ASR Leaderboard 29%, Picovoice speech-to-text-benc… 8% and 2 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%MIT
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇ 29%Apache-2.0
Picovoice speech-to-text-benchmark · English batch-engine WER (README)1▇▇▇ 8%Apache-2.0
AfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented English1▇ 5%CC BY 4.0
Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models1▇ 2%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 44.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json