MMS 1b All
Meta · released May 27, 2023 · facebook/mms-1b-all
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Languages
- 129
- Size
- 1B
Context measured in tokens · download allowed, licence restricts use
Our take
Written Sep 4, 2026MMS 1b All is a one-billion-parameter speech-to-text model from Meta with coverage of 129 languages. It is extremely fast and free for research use, but its accuracy trails most peers on every measured condition and it cannot be used commercially.
Pick this for research or non-commercial projects where you need broad language coverage and speed matters more than precision — it processes an hour of audio in roughly two seconds on benchmark hardware. Skip it if you need commercial deployment, accurate transcription of meetings or accented speech, or if you want a hosted provider rather than self-hosting.
The case for it
- Processes audio at nearly two thousand times real time — an hour of audio in about two seconds on benchmark hardware.
- Covers 129 languages, from Abkhaz to Aymara, which few transcription models match.
The case against it
- Accuracy lags behind most models on every measured condition: overall word error is more than double the median across 74 models, and it is tied for worst on podcasts, video and meetings.
- Non-commercial licence only: no commercial use, fine-tuning or redistribution permitted.
- No hosted providers listed; you must run it yourself.
How good is it?
An open speech-to-text model for turning recordings into written text, though its transcription is weaker than most on the recordings measured.
- transcribing recordings of meetings in a roomRecorded meetings · 91st of 92
- transcribing podcasts and video audioPodcasts and video · 91st of 92
- transcribing clear recordings of people reading aloudClean read speech · 84th of 92
TranscriptionTurning speech into text
1,954×27th of 74
an hour of audio in 2 seconds, on the board's own hardware. Your machine will differ.
129
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
Which languages ↓ ↑
ab · Afrikaans · Akan · Amharic · Arabic · Assamese · av · Aymara · Azerbaijani · ba · Bambara · Belarusian · Bangla · bi · bo · Serbian (Latin) · Breton · Bulgarian · Catalan · Czech · ce · cv · Kurdish · Welsh · Danish · German · Divehi · dz · Greek · English · Esperanto · Estonian · Basque · Ewe · Faroese · Persian · fj · Finnish · French · Western Frisian · ff · Irish · Galician · Guarani · Gujarati · Chinese · Haitian Creole · Hausa · Hebrew · Hindi · Hungarian · Armenian · Igbo · Interlingua · Malay · Icelandic · Italian · Javanese · Japanese · Kannada · Georgian · Kazakh · kr · Khmer · ki · Kinyarwanda · Kyrgyz · Korean · kv · Lao · Latin · Latvian · Lingala · Lithuanian · Luxembourgish · Ganda · mh · Malayalam · Marathi · Macedonian · Malagasy · Maltese · Mongolian · Māori · Burmese · Dutch · Norwegian · Nepali · Nyanja · Occitan · Oromo · Odia · os · Punjabi · Polish · Portuguese · Pashto · Quechua · Romanian · rn · Russian · sg · Slovak · Slovenian · Samoan · Shona · Sindhi · Somali · Spanish · Albanian · Sundanese · Swedish · Swahili · Tamil · Tatar · Telugu · Tajik · Filipino · Thai · Tigrinya · Tsonga · Turkish · Ukrainian · Vietnamese · Wolof · Xhosa · Yoruba · Zulu · za
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 20.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.1 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.1 GB spare means a 10% error in the size would not change the answer.
These cards answer whether MMS 1b All loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsCreative Commons Attribution-NonCommercial 4.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- facebook/mms-1b-all
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- facebook-mms-1b-all