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 Sep 4, 2026Wav2vec2 Large is a tiny downloadable speech-to-text model from Meta that turns English audio into text almost instantly. Released in 2022 with 0.3 billion parameters, it excels on clean read-aloud audio but degrades sharply on anything noisier.
Use this for batch transcription of clean English audiobooks where throughput matters more than perfect accuracy, or for research into open wav2vec 2.0 architectures under a permissive licence. Skip it if your audio includes accents, multiple speakers, background noise, or any language other than English.
The case for it
- Processes audio at roughly three thousand times real time — an hour of audio in about a second on benchmark hardware.
- Apache 2.0 licence allows commercial use, modification and redistribution.
- 1.36% word error rate on clean read-aloud audio, better than most models on this condition.
The case against it
- Error rate jumps to roughly one in four words on recorded meetings and one in seven on accented speech — worse than most models on every condition except clean speech.
- No commercial hosting available; you must run it yourself.
- Every accuracy figure is English-only; nothing we hold measures other languages.
How good is it?
An open speech-to-text model for turning recordings into written text, though meeting and podcast audio are its weakest ground.
- transcribing recordings of meetings in a roomRecorded meetings · 89th of 92
- transcribing podcasts and video audioPodcasts and video · 88th of 92
TranscriptionTurning speech into text
3,010×22nd of 74
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; the placing beneath each rate is against every model measured on that set.
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. 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.
These cards answer whether Wav2vec2 Large 960h Lv60 Self 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 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
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- facebook-wav2vec2-large-960h-lv60-self