whatmodel.sh / stt / Whisper tiny.en

Whisper tiny.en

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

Whisper tiny.en is an open-weights speech-to-text model from OpenAI, released September 2022. Its published size is 0.039B parameters. Licence: apache-2.0.

Catalogue identity notes

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

27.1±2.8#147 of 162 speech-to-text modelsfrom 7 benchmark results across 4 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 tiny.en, out of 176 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
159Moonshine Tiny Useful Sensors (Moonshine AI)29±3local~0.6GB2024-10
160Moonshine Streaming Tiny Useful Sensors (Moonshine AI)28±3local~0.7GB2026-01
161Whisper tiny.en OpenAI27±3local~0.6GB2022-09
162MMS-1B-all Meta25±3local~5.1GB2023-05
163Whisper base OpenAI25±3local~0.7GB2022-09
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 tests6 not in a task · 97% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER +15.8% ✎▁···▁▃▂·▄▄██ beats 2/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%blunt · several runs
Open ASR English short-form WER (March 2026)12.8% ✎▁▁▁▃··▃▁▂██▆ beats 13/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇ 26%blunt
FLEURS English test WER10.7% ✎▁··▁▁▁▃▁▁▃█▁ beats 5/56avg 5.8%▇▇▇▇▇ 13%blunt
Picovoice STT benchmark · English streaming 4-set mean WER22.4% ✎█·█···▄▄▄··▄ beats 1/7avg 8.3%▇▇▇▇▇ 13%typical
Picovoice STT benchmark · English batch 4-set mean WER12.7% ✎▄···▄···▄··█ beats 0/4avg 5.7%▇▇▇ 7.6%blunt
TED-LIUM test WER (short-form)13.7% ✎▂····▂▂▂█▃▃▂ beats 7/13avg 9.2%▇ 1.9%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~0.59 GB · from github.com/openai (official)
    uvx --from openai-whisper whisper audio.mp3 --model tiny.en

Official weights and documentation: huggingface.co/openai ↗

$ how the score was worked out · transcribe.cpp model catalog… 47%, Open ASR Leaderboard 26%, Picovoice speech-to-text-benc… 20% and 1 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%MIT
Open ASR Leaderboard1▇▇▇▇▇▇▇▇ 26%Apache-2.0
Picovoice speech-to-text-benchmark · English batch-engine WER (README)2▇▇▇▇▇▇ 20%Apache-2.0
Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models2▇ 3%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 27.1

$ 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