Wav2vec2 Large 960h Lv60 Self
Meta · released Mar 2, 2022 · facebook/wav2vec2-large-960h-lv60-self
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 1
- Size
- 0.3B
Context measured in tokens
Our take
Written Aug 3, 2026Wav2vec2 Large is a 0.3-billion-parameter English speech-to-text model released by Meta in 2022. It is extremely fast and permissively licensed, but its accuracy drops sharply on anything other than clean, read-aloud audio.
Pick this for batch transcription of clean, read-aloud English audio where raw speed matters — it processes an hour of audio in about a second on benchmark hardware. Use it for offline or local deployment with a permissive licence. Skip it if your audio includes meetings, accented speakers, or podcasts, where its error rate rises seventeen- to nineteen-fold; or if you need languages other than English, or any commercial hosted option.
The case for it
- Extremely fast: processes audio at roughly three thousand times real time on benchmark hardware.
- Strong on clean read-aloud English, with about one word in seventy wrong.
- Apache 2.0 licence allows commercial use and redistribution.
The case against it
- Accuracy collapses on challenging audio: meeting recordings are nineteen times worse than clean speech, and accented speech is seventeen times worse.
- English only; no other languages are measured or supported.
- No commercial hosting is available in our data.
How good is it?
TranscriptionTurning speech into text1 of 5Open ASR WER · 72nd of 74
88.2%
Misses roughly one word in 8, averaged over nine English test sets.
3,010×15th of 62
an hour of audio in 1 seconds, on the board's own hardware. Your machine will differ.
1
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, not to the board.
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.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 21.4 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. 22.6 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.6 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
When we formed this view
Dates behind this page
Prices last checked 6h ago
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 allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- facebook/wav2vec2-large-960h-lv60-self
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- facebook-wav2vec2-large-960h-lv60-self