Thanks @lucadellalib for this PR. Everything works smoothly. I have some comments regarding formatting:
All recipes should follow the same structure: dataset/task/architecture/. Please follow the same format as in the discriminative tasks in the DASB branch, here.
We should have the same script as discriminative rask for generative tasks. Please make sure, everything is consistent and compatible with the instructions in readme fil. For example the name of the py ad YAML.
The kmeans repository is transferred to speechbrain/SSL_Quantization, please update it in your recipe.
Thanks @lucadellalib for this PR. Everything works smoothly. I have some comments regarding formatting:
dataset/task/architecture/
. Please follow the same format as in the discriminative tasks in the DASB branch, here.