Skip to content

Mixer-TTS sup_data_path and sup_data_types #3793

Answered by redoctopus
oytunturk asked this question in Q&A
Discussion options

You must be logged in to vote

You can use this script to do it for the datasets in the .../dataset_processing/tts/ directory (or your own if you build your own YAML configs): https://github.com/NVIDIA/NeMo/blob/main/scripts/dataset_processing/tts/extract_sup_data.py

But yes, essentially the TTSDataset class will extract these automatically during training, which is what the above script uses to do so. Specifically they happen in these functions in TTSDataset:

def add_align_prior_matrix(self, **kwargs):
self.align_prior_matrix_folder = kwargs.pop('align_prior_matrix_folder', None)
if self.align_prior_matrix_folder is None:

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@oytunturk
Comment options

Answer selected by oytunturk
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
2 participants