Project AURIONAI Use-Cases Research & Innovation
NVIDIA
speaker

TitaNet

Speaker embedding model for speaker verification and diarization.

NVIDIANVIDIAUSA
Figure from the TitaNet paper: TitaNet Encoder and Decoder Architecture.
Levelmodel
Classspeaker
Parameters23M
Contextnot in the notes
Released8 Oct 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

R&D Topics

Speaker verification embeddingsexemplar

Identity

Developer
NVIDIA
Family
not in the notes
Released
8 Oct 2021 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
CNN 1D depth-wise separable convolutions with squeeze-and-excitation
Total parameters
23M sources
Active parameters
–
Checkpoint parameters
–
Note
TitaNet-Large is about 23M.
Context length
not in the notes
Input
audio
Output
not in the notes
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.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2110.04410 https://arxiv.org/abs/2110.04410
  2. huggingface.co/nvidia/speakerverification_en_titanet_large https://huggingface.co/nvidia/speakerverification_en_titanet_large

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