whatmodel.sh / stt / MMS-1B-FL102

MMS-1B-FL102

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

MMS-1B-FL102 is an open-weights speech-to-text model from Meta, released May 2023. Its published size is 0.96B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact checkpoint facebook/mms-1b-fl102 (default English adapter, as the card's example). Weights CC-BY-NC-4.0. Params: HF safetensors total. released: HF repo creation month.

-9.4±4.8#161 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 MMS-1B-FL102, out of 176 with a score, then more from Meta.

#modelscorewhereRAMreleased
172wav2vec 2.0 Large 960h Meta7±3local~2GB2020-06
173data2vec Audio Base 960h Meta4±4local~1GB2022-02
174wav2vec 2.0 Base 960h Meta2±3local~1GB2020-06
175MMS-1B-FL102 Meta-9±5local~5.1GB2023-05
176MedASR Google-14±4local~0.1GB2025-12
more from Meta
1Muse Voice Transcribe 1.0 Meta71±3api $0.0030/audio min2026-09
58Omnilingual ASR LLM 7B Meta58±2local~19GB2025-11
59Omnilingual ASR LLM 7B v2 Meta58±3local~19GB2025-12

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

$ what it's good at

other tests3 not in a task · 91% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)39.8% ✎▃▁▁▃··▁▁▂██▆ beats 0/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%blunt
TED-LIUM test WER (short-form)30.2% ✎▃····▂▂▂█▃▃▂ beats 0/13avg 9.2%▇▇ 5.9%blunt
LibriSpeech test-clean WER15.4% ✎▃··▂·▃▂█▂▃▃▃ beats 0/16avg 1.7%▇▇ 4.6%blunt · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~5.11 GB · from huggingface.co/facebook
    uv run --with transformers --with torch python -c "from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='facebook/mms-1b-fl102', chunk_length_s=30)('audio.wav')['text'])"

Weights and documentation: huggingface.co/facebook ↗

$ how the score was worked out · Open ASR Leaderboard 81%, Speech Robust Bench (arXiv:24… 10%

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
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%Apache-2.0
Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models2▇▇▇ 10%CC BY 4.0
prior · pull toward the middle▇▇▇ 9%
weighted average= -9.4

$ 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