whatmodel.sh / stt / Omnilingual ASR LLM 1B v2

Omnilingual ASR LLM 1B v2

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

Omnilingual ASR LLM 1B v2 is an open-weights speech-to-text model from Meta, released December 2025. Its published size is 2.28B parameters. Licence: apache-2.0.

Catalogue identity notes

Omnilingual ASR model card 'omniASR_LLM_1B_v2' (checkpoint https://dl.fbaipublicfiles.com/mms/omniASR-LLM-1B-v2.pt, listed in src/omnilingual_asr/cards/models/rc_models_v2.yaml @ 81f51e2; 'December 2025 Update'). Not on Hugging Face; the CSV entry 'facebook/omniASR-LLM-1B-v2' is the leaderboard's label. Distinct from the v1 checkpoint of the same size. Params: README table. Needs libsndfile (README).

55.6±2.8#64 of 162 speech-to-text modelsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

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 LLM 1B v2, out of 176 with a score, then more from Meta.

#modelscorewhereRAMreleased
73Parakeet TDT-CTC 1.1B NVIDIA56±4local~1.3GB2024-05
74GPT-4o Mini Transcribe OpenAI56±2api $0.0030/audio min2025-03
75Omnilingual ASR LLM 1B v2 Meta56±3local~6GB2025-12
76Omnilingual ASR LLM 1B Meta56±2local~6GB2025-11
77Distil-Whisper distil-large-v3 Hugging Face (Distil-Whisper)56±2local~2.3GB2024-03
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▂··▃▄█▆▅▄▂·▂ #11 of 36 * · 97% of its score · 2 tests

Beats Cohere Transcribe Arabic (07-2026), Qwen3-ASR-1.7B, Voxtral Mini Transcribe V2 here, though they rank higher overall. Trails SeamlessM4T v2 Large here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Open ASR multilingual WER6.1% ✎▂··▂▃▂█▃█▂▁▁ beats 13/29avg 8.9%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%typical
Iberian ASR benchmark · 7-language macro WER (eu, ca, gl, pt, es + de, tr)16.6% ✎█▃▃··▅▃▃··▃▃ beats 8/10avg 38%▇▇ 4.6%noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~5.97 GB · from github.com/facebookresearch (official)
    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_LLM_1B_v2').transcribe(['audio.wav'], batch_size=1))"

Official weights and documentation: github.com/facebookresearch ↗

$ how the score was worked out · Open ASR Leaderboard 92%, Benchmarking Automatic Speech… 5%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%Apache-2.0
Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 31▇ 5%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 55.6

$ 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