I wan to try WavLM for 2 tasks:

  1. Speaker Verification
  2. Speech embeddings

If I understand it correctly, the WavLM pre-trained model was trained on English.

so if I want to use it for my missions, do I need to fine-tune it for Portuguese? or because the basic was trained only on English - I need to train it from scratch on Portuguese?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.