NVIDIA TitaNet-Large is a speaker embedding model trained on English speech for speaker verification, recognition, and diarization tasks. It is part of the NVIDIA NeMo framework and can extract embeddings from audio for downstream verification or clustering. The model card provides usage examples for embedding extraction and verification of utterances.
In the Other AI space, Speakerverification En Titanet Large takes a focused approach. It focuses on extracting speaker embeddings and performing speaker verification or diarization on English audio without training a custom model. Speakerverification En Titanet Large is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
NVIDIA builds and maintains Speakerverification En Titanet Large, and it first shipped in 2019. The project is developed in the open on GitHub with 17.8k stars and 141 commits in the last 90 days. Key capabilities include Speaker Embeddings, Speaker Verification, and Speaker Diarization.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match