Microsoft's WavLM Large is a proprietary embedding model designed for speech processing. It takes audio as input and outputs embeddings, with a focus on both spoken content modeling and speaker identity preservation.
Input
Output
Context
-
Max Output
n/a
Parameters
-
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
None the catalog can show from stated facts or measured scores.
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
Microsoft has not published a context window for WavLM Large. The catalog does not estimate one.
No. WavLM Large is not released under an open license. Use it through Microsoft's API or a provider that serves it.
Microsoft has not published a parameter count for WavLM Large. The catalog does not estimate undisclosed sizes.
WavLM Large accepts Text and produces Embedding. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for WavLM Large yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves WavLM Large, and Inferbase runs it on your account with the same routing and logs.
Microsoft does not publish open weights for WavLM Large, so it runs through an API: Microsoft's own, or Inferbase where it is served.
The model card of WavLM Large lists one language: English. That is what Microsoft states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.