Project AURIONAI Use-Cases Research & Innovation
speech recognitionfamily

Parakeet-TDT-0.6B

NVIDIA fast ASR model; v3 adds 25 European languages.

NVIDIANVIDIAUSA
NVIDIA
Levelfamily
Classspeech recognition
Parameters600M
Contextnot in the notes
Released2025
Opennessopen weights permissive
Runs onsingle datacentre GPU, CPU server
Statusactive

Benchmark Results

maintainer-run
Hugging Face Open ASR Leaderboardspeech
Parakeet-TDT-0.6B v2eight-set macro-average English WERmaintainer-run
6.05
snapshot 2026-05-06 via benchmarklist6 May 2026 benchmarklist.com
Parakeet-TDT-0.6B v3eight-set macro-average English WERmaintainer-run
6.32
048

Score in WER. Lower is better.

snapshot 2026-05-06 via benchmarklist6 May 2026 benchmarklist.com
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

NVIDIAParakeet-TDT-0.6B v2 belongs to this familyspeech recognition2025600M
NVIDIAParakeet-TDT-0.6B v3 belongs to this familyspeech recognition2025600M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Massively multilingual speech recognitionproduced byStreaming and low-latency speech recognitionproduced by

Identity

Developer
NVIDIA
Family
not in the notes
Released
2025 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
other FastConformer + TDT (CTC/TDT), much faster than LLM-decoder models
Total parameters
600M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
audio
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Creative Commons Attribution 4.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU, CPU server
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. Gladia - Best open-source speech-to-text models in 2026 gladia.io https://www.gladia.io/blog/best-open-source-speech-to-text-models
  2. Open ASR Leaderboard Benchmark Scores & AI Model Leaderboard | BenchmarkList benchmarklist.com https://benchmarklist.com/benchmarks/open_asr_leaderboard/

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Parakeet-TDT-0.6B", https://aurion.semai.id/models/nvidia-parakeet-tdt-0-6b/, records of October 2026.