ESPnet
102 languages
audio
self-supervised-learning
speech-recognition

How to use this model to fine-tune using own data?

#1
by Yehor - opened

The question is in the subject

You can follow this colab notebook that uses ESPnet to finetune it.
Or you can directly add it to any pytorch module you have using S3PRL: https://s3prl.github.io/s3prl/tutorial/upstream_collection.html#wavlablm

Sign up or log in to comment