Lite Whisper Large v3 Acc
Efficient Speech · released Feb 26, 2025 · efficient-speech/lite-whisper-large-v3-acc
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 99
- Size
- 1.4B
Context measured in tokens
Our take
Written Aug 3, 2026Lite Whisper Large v3 Acc is a compact downloadable speech-to-text model that turns audio into written words across 99 languages. It is built for speed, processing an hour of audio in about 18 seconds on benchmark hardware, though every accuracy figure we hold is English-only.
Pick this for fast batch transcription or multilingual deployment with a permissive licence. Use it for clean read-aloud or financial calls where 1.6–2.6% word error rate suffices. Skip it if you need verified non-English accuracy, accented or meeting audio, or hosted rather than self-hosted inference.
The case for it
- Extremely fast transcription: 204 times real-time on benchmark hardware, or roughly one hour of audio in 18 seconds.
- Broad language coverage for a downloadable model, with 99 languages supported.
- Strong on clean, structured English audio: 1.6% word error rate on read-aloud, 2.62% on financial calls.
- Truly permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
The case against it
- Accuracy collapses in challenging acoustic conditions: 10.7% word error rate on accented speech, more than six times worse than on clean read-aloud.
- No verified accuracy in any language except English, despite the 99-language claim.
- No commercial hosting available; zero current offers mean you must self-host.
How good is it?
TranscriptionTurning speech into text2.5 of 5Open ASR WER · 47th of 74
93.7%
Misses roughly one word in 16, averaged over nine English test sets.
204×48th of 62
an hour of audio in 18 seconds, on the board's own hardware. Your machine will differ.
99
Stated by the leaderboard; we do not hold the list itself.
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. 20.7 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. 21.9 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. 3.9 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
- efficient-speech/lite-whisper-large-v3-acc
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- efficient-speech-lite-whisper-large-v3-acc