Parakeet TDT CTC 110m
NVIDIA · released Sep 17, 2024 · nvidia/parakeet-tdt_ctc-110m
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 1
- Size
- 0.1B
Context measured in tokens
Our take
Written Aug 3, 2026Parakeet is NVIDIA's tiny downloadable speech-to-text model built for blistering speed on clean English audio. At 0.11 billion parameters it fits almost anywhere, but its accuracy gap between easy and hard conditions is severe.
Pick this for offline batch transcription of clean, read-aloud English audio where throughput matters most — it processes an hour of audio in under a second on benchmark hardware. Use it for edge or local deployment with a tiny footprint, or for financial call transcription where it keeps errors low. Skip it if your audio is messy, accented, or multilingual, or if you need hosted inference rather than self-hosting.
The case for it
- Extremely fast: 6,118.84 times real time on benchmark hardware.
- Strong on clean, scripted audio with about one word in fifty wrong on read speech, and similarly low on financial calls.
- Creative Commons Attribution 4.0 licence allows commercial use with attribution.
- 0.11 billion parameters, small enough for severely resource-constrained deployment.
The case against it
- Accuracy collapses on challenging audio: recorded meetings are more than six times worse than clean read speech.
- English only; all accuracy figures are English and no other language is supported.
- No hosted inference options available in our data; you must run it yourself.
How good is it?
TranscriptionTurning speech into text2 of 5Open ASR WER · 55th of 74
93.4%
Misses roughly one word in 15, averaged over nine English test sets.
6,119×1st 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. 21.5 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. 22.7 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. 4.7 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 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-tdt_ctc-110m
- Modality record
- audio->text
- Catalogue slug
- nvidia-parakeet-tdt-ctc-110m