Distil Large v3.5
Distil-Whisper · released Dec 5, 2024 · distil-whisper/distil-large-v3.5
Speech to textTranscribes a recording into words
- Type
- Open weightsMIT License
- Languages
- 1
- Size
- 0.8B
Context measured in tokens
Our take
Written Aug 3, 2026Distil Large v3.5 is a tiny downloadable speech-to-text model built for speed over accuracy. It turns English audio into written text at 874 times real-time speed on benchmark hardware, with a permissive MIT licence that places no restrictions on commercial use.
Pick this for offline batch transcription where throughput beats precision, or for clean audio like read-aloud and financial calls where error rates sit below three percent. Use it when you need a fully permissive licence with no hosting dependency. Skip it if you need non-English languages, noisy or accented audio, or managed hosting rather than self-hosting.
The case for it
- Extremely fast transcription at 874 times real-time on benchmark hardware.
- Strong on clean, structured audio: about one word in fifty wrong on read-aloud, and similar on financial calls.
- Fully permissive MIT licence with no commercial restrictions beyond the licence text itself.
The case against it
- Accuracy collapses in challenging acoustic conditions: error rate on accented speech is more than five times worse than on read-aloud.
- Only one language supported, with no measured accuracy for any other language.
- No commercial hosting available in our catalogue — you must self-host or integrate manually.
How good is it?
TranscriptionTurning speech into text2.5 of 5Open ASR WER · 44th of 74
93.9%
Misses roughly one word in 16, averaged over nine English test sets.
874×25th of 62
an hour of audio in 4 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. 21.1 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. 22.3 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. 4.3 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 allowsMIT License, 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
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- distil-whisper/distil-large-v3.5
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- distil-whisper-distil-large-v3-5