Wavlm Base Plus
Microsoft's WavLM-Base-Plus is an open-source embedding model pretrained on 16kHz sampled speech audio, totaling 94,000 hours of training data from Libri-Light, GigaSpeech, and VoxPopuli datasets. It is genuinely best at generating embeddings for speech-related tasks, although it requires fine-tuning and a custom tokenizer for speech recognition applications.
Input
Output
Context
-
Max Output
-
Parameters
94.7M
Technical Specifications
Model TypeEmbedding
Context WindowNot available
Max Output TokensNot available
Parameters94.7M
Release DateMar 2, 2022
Training CutoffNot available
LicenseMIT
Open SourceYes
Input Modalities
Text
Output Modalities
Embedding
Capabilities
Resources & Links
Estimated GPU Requirements for Wavlm Base Plus
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.