This model integrates pyannote and wespeaker technologies trained on the VoxCeleb dataset. It produces speaker embeddings and supports speaker diarization and verification tasks. It is distributed as an open-weight model for use with PyTorch.
Pyannote Wespeaker Voxceleb Resnet34 LM is an Other models project. It focuses on identifying and separating different speakers within an audio recording. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web and API.
Revai builds and maintains Pyannote Wespeaker Voxceleb Resnet34 LM.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do