speech recognitionfamily
Parakeet
NVIDIA NeMo family of FastConformer speech recognition models with CTC, transducer and TDT decoders.
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released28 Dec 2023
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Lineage
parakeet-unified-en-0.6b belongs to this familyspeech recognition7 Apr 2026600Mmultitalker-parakeet-streaming-0.6b-v1 belongs to this familyspeech recognition15 Oct 2025600Mparakeet-tdt_ctc-110m belongs to this familyspeech recognition17 Sep 2024114Mparakeet-tdt-1.1b belongs to this familyspeech recognition25 Jan 2024parakeet-ctc-1.1b belongs to this familyspeech recognition28 Dec 20231.06Bparakeet-rnnt-1.1b belongs to this familyspeech recognition27 Dec 20231.07BWhere 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.
Identity
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 encoder with CTC, RNN-T or TDT decoders
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 110M to 1.1B; checkpoints include parakeet-ctc-0.6b, parakeet-ctc-1.1b, parakeet-rnnt-0.6b, parakeet-rnnt-1.1b, parakeet-tdt-1.1b, parakeet-tdt_ctc-110m, parakeet-tdt_ctc-0.6b-ja, parakeet-unified-en-0.6b. The Parakeet-TDT-0.6B line has its own AURION family.
- 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
- not in the notes
- 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
- Mostly English; one Japanese checkpoint
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperNVIDIAbig tech, USA
NVIDIAbig tech, USAModelParakeetNVIDIA, speech recognition
ParakeetNVIDIA, speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Models 6
multitalker-parakeet-streaming-0.6b-v1NVIDIA, speech recognitionFamilyparakeet-ctc-1.1bNVIDIA, speech recognitionFamilyparakeet-rnnt-1.1bNVIDIA, speech recognitionFamilyparakeet-tdt_ctc-110mNVIDIA, speech recognitionFamilyparakeet-tdt-1.1bNVIDIA, speech recognitionFamilyparakeet-unified-en-0.6bNVIDIA, speech recognitionFamilyOrganisations 1
Sources
- huggingface.co/nvidia/parakeet-ctc-1.1b https://huggingface.co/nvidia/parakeet-ctc-1.1b
- docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/... https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/all_chkpt.html
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Parakeet", https://aurion.semai.id/models/nvidia-parakeet/, records of October 2026.