whatmodel.sh / stt / Omnilingual ASR CTC 300M

Omnilingual ASR CTC 300M

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

Omnilingual ASR CTC 300M is an open-weights speech-to-text model from Meta, released November 2025. Its published size is 0.33B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact checkpoint facebook/omniASR-CTC-300M (fairseq2 card 'omniASR_CTC_300M', first Omnilingual ASR release, Nov 2025); distinct from its '_v2' successor. Params: card table. Needs libsndfile (card).

44.6±2.4#124 of 162 speech-to-text modelsfrom 4 benchmark results across 3 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 Omnilingual ASR CTC 300M, out of 176 with a score, then more from Meta.

#modelscorewhereRAMreleased
135ESPnet wav2vec 2.0 Large + Conformer + Transformer LM ESPnet45±4local~8GB2021-12
136ESPnet Conformer + S4 decoder (no LM) ESPnet45±4local~8GB2022-12
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
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

multilingual transcription▃··▃▄█▆▅▄▂·▂ #36 of 36 * · 67% of its score · 1 test

Trails Omnilingual ASR CTC 300M v2 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Open ASR multilingual WER14.9% ✎▃··▂▃▂█▃█▂▁▁ beats 0/29avg 8.9%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%typical
other tests3 not in a task · 30% of its score
testresultvs the others in its rundifficultycountswhy
Omnilingual ASR paper · FLEURS-81 test mean CER (Whisper-covered languages) lab11.8% ✎▅···▃···▃▃██ beats 3/10avg 13%▇▇▇▇▇▇ 14%sharp · noisy
Omnilingual ASR paper · Common Voice 22 (76 languages) test mean CER lab17.6% ✎▂▂▂····▃▆··█ beats 3/10avg 21%▇▇▇▇ 10%sharp · noisy
Open Universal Arabic ASR Leaderboard · 6-test-set average WER46.7% ✎▃·▃▂▅█▅▃▂▅▂▂ beats 2/22avg 40%▇▇ 5.8%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.29 GB · from huggingface.co/facebook
    uv run --python 3.12 --with omnilingual-asr python -c "from omnilingual_asr.models.inference.pipeline import ASRInferencePipeline as P; print(P(model_card='omniASR_CTC_300M').transcribe(['audio.wav'], batch_size=1))"

Weights and documentation: huggingface.co/facebook ↗

$ how the score was worked out · Open ASR Leaderboard 67%, Omnilingual ASR: Open-Source… 25%, Open Universal Arabic ASR Lea… 6%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%Apache-2.0
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1) · lab-reported2▇▇▇▇▇▇▇ 25%CC BY-SA 4.0
Open Universal Arabic ASR Leaderboard (Elm Research Center)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 44.6

$ 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