Parakeet CTC 1.1b
NVIDIA · released Dec 28, 2023 · nvidia/parakeet-ctc-1.1b
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 1
- Size
- 1.1B
Context measured in tokens
Our take
Written Aug 3, 2026Parakeet CTC is a tiny downloadable speech-to-text model from NVIDIA that turns English audio into written words at extraordinary speed. It is near-flawless on clean read-aloud recordings but its accuracy collapses on podcasts, meetings and accented speech.
Pick this for batch transcription of clean, scripted English where speed matters more than nuance, or for edge deployment with permissive licensing. Skip it if you need commercial hosting, non-English languages, or reliable accuracy on natural conversation or accented speakers.
The case for it
- Extremely fast transcription: roughly one hour of audio in under a second on the benchmark hardware.
- Near-flawless on clean read-aloud English, with only 1.5% of words wrong.
- Permissive Creative Commons Attribution 4.0 licence allows commercial use and redistribution with attribution.
The case against it
- Accuracy degrades sharply in natural, multi-speaker or accented settings: error rate jumps more than eightfold in recorded meetings and on accented speech compared with clean read-aloud.
- No commercial hosting options currently available; users must self-host.
- English only; no source we hold measures accuracy in any other language.
How good is it?
TranscriptionTurning speech into text2.5 of 5Open ASR WER · 53rd of 74
93.5%
Misses roughly one word in 15, averaged over nine English test sets.
5,015×6th of 62
an hour of audio in under a second, 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. 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.
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 →
Models people weigh against Parakeet CTC 1.1b
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 allowsCreative Commons Attribution 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 4.0
Permissive content license: any use with attribution. Common for datasets and some model weights.
Identifiers
- Hugging Face
- nvidia/parakeet-ctc-1.1b
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- nvidia-parakeet-ctc-1-1b