Wespeaker: A Research And Production Oriented Speaker Embedding Learning Toolkit

Abstract

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.

Stats

• citations0
• S2 citations—
• github stars1283
• HF likes0
• heat score6.22
• arxiv keywang2022wespeaker

Code

• wenet-e2e/wespeaker—

Related papers

• Espnet-spk: Full Pipeline Speaker Embedding Toolkit With Reproducible Recipes, Self-supervised Front-ends, And Off-the-shelf Models (2024)0.00
• Overview Of Speaker Modeling And Its Applications: From The Lens Of Deep Speaker Representation Learning (2024)10.74
• 3d-speaker-toolkit: An Open-source Toolkit For Multimodal Speaker Verification And Diarization (2024)6.93
• How To Improve Your Speaker Embeddings Extractor In Generic Toolkits (2018)9.76
• Whisper Speaker Identification: Leveraging Pre-trained Multilingual Transformers For Robust Speaker Embeddings (2025)0.00
• ECAPA2: A Hybrid Neural Network Architecture And Training Strategy For Robust Speaker Embeddings (2024)0.00
• Improving Speaker Identification For Shared Devices By Adapting Embeddings To Speaker Subsets (2021)4.52
• Fine-tuning Wav2vec2 For Speaker Recognition (2021)18.88