whatmodel.sh / stt / Omnilingual ASR CTC 1B v2
Omnilingual ASR CTC 1B v2
↗ share
+ contribute
Omnilingual ASR CTC 1B v2 is an open-weights speech-to-text model from Meta, released December 2025. Its published size is 0.98B parameters. Licence: apache-2.0.
Catalogue identity notes
Omnilingual ASR model card 'omniASR_CTC_1B_v2' (checkpoint https://dl.fbaipublicfiles.com/mms/omniASR-CTC-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-CTC-1B-v2' is the leaderboard's label. Distinct from the v1 checkpoint of the same size. Params: README table. Needs libsndfile (README).
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 1B v2, out of 176 with a score, then more from Meta.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 114 |  OWSM-CTC v3.1 1B | 50±4 | local | ||
| 115 |  Multitalker Parakeet Streaming 0.6B v1 | 50±4 | local | ||
| 116 | Omnilingual ASR CTC 1B v2 | 50±3 | local | ||
| 117 |  Whisper large (v1) | 49±2 | local | ||
| 118 | OWSM-CTC v3.2 ft 1B | 49±4 | local | ||
| more from Meta | |||||
| 1 | Muse Voice Transcribe 1.0 | 71±3 | api $0.0030/audio min | ||
| 58 | Omnilingual ASR LLM 7B | 58±2 | local | ||
| 59 | Omnilingual ASR LLM 7B v2 | 58±3 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
multilingual transcription▂··▃▄█▆▅▄▂·▂ #14 of 36 * · 87% 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.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR multilingual WER | 8.0% ✎ | ▂··▂▃▂█▃█▂▁▁ beats 6/29 | 83% |
| Iberian ASR benchmark · 7-language macro WER (eu, ca, gl, pt, es + de, tr) | 21.5% ✎ | █▃▃··▅▃▃··▃▃ beats 6/10 | 4.2% |
other tests2 not in a task · 10% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Betthupferl (German dialect ASR benchmark) · Standard German audio → Standard German transcript WER | 23.9% ✎ | ▄·█·▄▄▄▄·█▄▄ beats 3/10 | 7.2% |
| Betthupferl (German dialect ASR benchmark) · dialect audio → Standard German transcript WER | 67.2% ✎ | ▃█····▃▅▃·▅▃ beats 2/10 | 3.2% |
$ where to run it
Other ways to run it
- Run it as published · needs ~2.85 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_CTC_1B_v2').transcribe(['audio.wav'], batch_size=1))"
Official weights and documentation: github.com/facebookresearch ↗
$ how the score was worked out · Open ASR Leaderboard 83%, German dialect ASR Benchmark… 10%, Benchmarking Automatic Speech… 4%
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
| source | results | share of the score |
|---|---|---|
 Open ASR Leaderboard | 1 | 83% |
| German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard) | 2 | 10% |
 Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3 | 1 | 4% |
| prior · pull toward the middle | 3% | |
| weighted average | = 49.5 |
$ improve this page
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