gst-tacotron
gst-tacotron copied to clipboard
syang1993
preprocessing the training data
Thank you very much for your nice work.
I have a problem with preprocessing the training data. The transcript file for Blizzard2013 segmented data is a file named prompts.gui which can be found here:
https://www.dropbox.com/s/6ugwnbqgwlfvxvl/prompts.gui?dl=0
I was wondering how the metdata.train file should look like. It seems that I need to clean up the attached file to be used for training and match the criteria. Is it possible to upload your cleaned up 'metadata-train' file, the converter of prompt.gui to metadata-train, or the desired format of the metadata.train file?
Hi, I just simply extract the text from the prompts.gui, ignoring other information like prosody.
You can get the file format from the attachment. metadata.zip
Hi, I just simply extract the text from the
prompts.gui, ignoring other information like prosody.You can get the file format from the attachment. metadata.zip
Do you know what the other information is? I can't understand what the 3rd line in prompt.gui mean. Following is an example
CA-BB-01-01 Black Beauty @ : # the Autobiography @ of a Horse . # B L 62iHfN KcF _ B y13iHfW ^ T Y2iLfN @ : || _ DH Y2iLfN cYa _ 33iHfN ^ T N42iLfN ^ B 6y2iLfN cY ^ 42iHfN ^ GcS R N41iLfN ^ F Y1iLfN cYa @ _ N41iLfN VcD _ N41iLfN _ H 32iHfW R ScT . ||
