Replies: 1 comment
-
Yes, the Kotoba (https://github.com/kotoba-tech/kotoba-speech-release) team finetuned the model to make it work in Japanese. My understanding is that they used the pretrained first stage model as a base model, and only finetuned this. The rest was kept fixed. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi all,
do someone know, if it is possible to finetune with an other language like german?
greeting
Al
Beta Was this translation helpful? Give feedback.
All reactions