whatmodel.sh / stt / Moonshine Base

Moonshine Base

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

Moonshine Base is an open-weights speech-to-text model from Useful Sensors (Moonshine AI), released October 2024. Its published size is 0.062B parameters. Licence: mit.

Catalogue identity notes

Exact checkpoint moonshine-ai/moonshine-base (CSV entry 'usefulsensors/moonshine-base'; the Hub redirects the old UsefulSensors org name). Params: HF safetensors total. released: card 'Release date: October 2024'.

37.8±3.2#141 of 162 speech-to-text modelsfrom 3 benchmark results across 2 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 Moonshine Base, out of 176 with a score, then more from Useful Sensors (Moonshine AI).

#modelscorewhereRAMreleased
153STT En Conformer-CTC Small NVIDIA39±3local~0.6GB2023-06
154Whisper small OpenAI39±2local~1.1GB2022-09
155Moonshine Base Useful Sensors (Moonshine AI)38±3local~0.8GB2024-10
156Whisper base.en OpenAI35±3local~0.7GB2022-09
157SpeechBrain wav2vec2 CTC (LibriSpeech) SpeechBrain35±4local~2GB2022-06
more from Useful Sensors (Moonshine AI)
108Moonshine Streaming Medium Useful Sensors (Moonshine AI)50±3local~1.8GB2026-01
132Moonshine Streaming Small Useful Sensors (Moonshine AI)46±3local~1.2GB2026-01
159Moonshine Tiny Useful Sensors (Moonshine AI)29±3local~0.6GB2024-10

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

$ what it's good at

other tests3 not in a task · 96% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER3.3% ✎▁···▁▁▂·▄▄██ beats 8/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%blunt
Open ASR English short-form WER (March 2026)10.0% ✎▁▁▁▃··▁▁▃██▆ beats 21/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%blunt
FLEURS English test WER12.3% ✎▁··▁▁▃▁▁▁▃█▁ beats 4/56avg 5.8%▇▇▇▇▇▇▇ 18%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.8 GB · from huggingface.co/moonshine-ai (official)
    uv run --with transformers --with torch python -c "from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='moonshine-ai/moonshine-base')('audio.wav')['text'])"

Official weights and documentation: huggingface.co/moonshine-ai ↗

$ how the score was worked out · transcribe.cpp model catalog… 62%, Open ASR Leaderboard 35%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%MIT
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇ 35%Apache-2.0
prior · pull toward the middle▇ 4%
weighted average= 37.8

$ 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