Project AURIONAI Use-Cases Research & Innovation
NVIDIA
speech recognitionfamily

FastConformer

Redesigned Conformer encoder that is 2.8 times faster and is the basis of the NeMo Parakeet and Canary models.

NVIDIANVIDIAUSA
Figure from the FastConformer paper: Fast Conformer combines local attention with a global context token to process long speech samples.
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released8 May 2023
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

NVIDIAstt_en_fastconformer_transducer_large belongs to this familyspeech recognition8 Jun 2023114M
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

Efficient acoustic encoder architectures for speech recognitionexemplar

Identity

Developer
NVIDIA
Family
not in the notes
Released
8 May 2023 sourcesannouncement page
Weights published
–
Record checked
12 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 Conformer redesigned with 8x downsampling and linearly scalable attention
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
NeMo publishes CTC, transducer and hybrid checkpoints in about 25 languages (stt_<lang>_fastconformer_*); Large is about 114M.
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
not in the notes
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.

Sources

  1. arxiv.org/abs/2305.05084 https://arxiv.org/abs/2305.05084
  2. huggingface.co/nvidia/stt_en_fastconformer_transducer_large https://huggingface.co/nvidia/stt_en_fastconformer_transducer_large

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "FastConformer", https://aurion.semai.id/models/nvidia-fastconformer/, records of October 2026.