WavLM paper points to UniSpeech #25367
Description
System Info
NA
Who can help?
Information
- The official example scripts
- My own modified scripts
Tasks
- An officially supported task in the
examplesfolder (such as GLUE/SQuAD, ...) - My own task or dataset (give details below)
Reproduction
transformers/src/transformers/models/wavlm/modeling_wavlm.py
Lines 1060 to 1063 in e42587f
https://arxiv.org/abs/2101.07597 is UniSpeech.
WavLM should be https://arxiv.org/abs/2110.13900 instead.
Expected behavior
NA