Speakerverification_en_titanet_large
NVIDIA's Speakerverification_en_titanet_large is an open-source audio model that excels at extracting speaker embeddings from speech, which is essential for speaker verification and diarization tasks. It is particularly effective due to its large size, with around 23M parameters, and its depth-wise separable conv1D architecture.
Input
Output
Context
-
Max Output
-
Parameters
23M
Technical Specifications
Model TypeAudio
Context WindowNot available
Max Output TokensNot available
Parameters23M
Release DateJul 15, 2022
Training CutoffNot available
Licensecc-by-4.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Embedding
Capabilities
Resources & Links
Estimated GPU Requirements for Speakerverification_en_titanet_large
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.