Parakeet TDT 0.6b v2
NVIDIA · released Apr 15, 2025 · nvidia/parakeet-tdt-0.6b-v2
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 1
- Size
- 0.6B
Context measured in tokens
Our take
Written Sep 4, 2026Parakeet is NVIDIA's tiny downloadable speech-to-text model, small enough to run on almost any device and fast enough to process an hour of audio in under a second. It is built for speed and local deployment rather than maximum accuracy.
Pick this when you need speech-to-text running locally or on edge hardware where speed is critical, or for English read-aloud and financial audio where it makes fewer errors than most models. Use it for meetings and podcasts where it still beats the field average despite harder audio pushing its error rate up several times. Skip it if you need multilingual coverage, the absolute best English accuracy, or a managed hosted service.
The case for it
- Processes audio at over six-thousand-times real-time speed — an hour of audio in under a second on benchmark hardware.
- Better than most models on every measured condition: read-aloud, podcasts, meetings and accented speech.
- Small enough to fit on almost any hardware: 0.6B parameters.
- Permissive Creative Commons licence allows commercial use with attribution.
The case against it
- Not the most accurate overall: 5.4% word error against 4.4% for the best model tracked.
- English only; no measured accuracy in any other language.
- No hosted providers listed; you must run it yourself.
How good is it?
TranscriptionTurning speech into text4 of 5Open ASR WER · 25th of 76
95.3%
Misses roughly one word in 21, averaged over nine English test sets.
6,025×10th of 74
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; 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 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?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 21.2 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. 22.4 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. 4.4 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Parakeet TDT 0.6b v2 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.
Models people weigh against Parakeet TDT 0.6b v2
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 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-0.6b-v2
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-parakeet-tdt-0-6b-v2