Omnilingual ASR by Meta
Shares rank 15 of 25 speech recognition models by recommenders
Free, openly downloadable speech recognition for many languages, praised for rare-language coverage. Critics doubt accuracy outside major languages and say the demo misheard many words.
Free, openly downloadable speech recognition for many languages, praised for rare-language coverage. Critics doubt accuracy outside major languages and say the demo misheard many words.
14 people gave an opinion
- recommend it
- 9
- criticize it
- 5
- approval share
- 64%
Recommended in 1 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 1.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Free, openly available, runs locally
“This seems like a massive improvement for openly available local ASR.”
Comment from 10 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” “Freely downloadable and usable by anyone for almost anything.”
Comment from 10 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” Seen as a major advance
“This seems like a massive improvement for openly available local ASR.”
Comment from 10 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” “First, let me say that this is impressive.”
Comment from 11 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages”
What people warn about
Each mark is one comment
Weak accuracy outside major languages
“it wins by supporting something rare well but never had good ASR accuracy even for Swedish etc.”
Comment from 11 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” “I highly doubt this model is anywhere near as good as it is on EU languages for most of them”
Comment from 11 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” Misrecognizes many words
“reduces the ability of the model to actually transcribe what was said”
Comment from 11 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages” “the hf demo misrecognized about half of the words”
Comment from 10 Nov 2025 in “Omnilingual ASR: Advancing automatic speech recognition for 1600 languages”
Other speech recognition models people recommend
The four most recommended other speech recognition models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| OpenAI Whisper | 164 | 53 | 76% | 12 | — | Approved |
| NVIDIA Parakeet | 144 | 27 | 84% | 12 | — | Approved |
| Mistral Voxtral | 69 | 27 | 72% | 8 | — | Approved |
| Moonshine open-weights STT models | 37 | 13 | 74% | 7 | — | Approved |
| Omnilingual ASR by MetaThis page | 9 | 5 | 64% | 1 | — | — |
What people said
All 15 comments that mention it, newest first. Each links to the original comment.
“There are others too like Meta's omnilingual one.”
“Omnilingual + OMSF ASR was intentionally curated to represent naturalistic”
“Are these really language-vulnerability ratings or did they just make a mapping from Trump's tariff rates?”
“I highly doubt this model is anywhere near as good as it is on EU languages for most of them”
“Additionally, the feedback mechanism seems also broken”
“reduces the ability of the model to actually transcribe what was said”
“you can not tune those models for practical applications”
“First, let me say that this is impressive.”
“it wins by supporting something rare well but never had good ASR accuracy even for Swedish etc.”
“The world just got smaller”
“What might be interesting is the newly released OmniASR data”
“the hf demo misrecognized about half of the words”
“Freely downloadable and usable by anyone for almost anything.”
“the global language explorer is fascinating -great work guys”
“This seems like a massive improvement for openly available local ASR.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.