nii-yamagishilab/multi-speaker-tacotron

Dataset

sunyuxiu opened this issue · 4 comments

Can you provide examples of runtime in your code, including all txt and wav.
I can not run your example with the path of /gs/hs0/tgh-19IAA/ecooper/data/vctk0.91-preprocessed-phone/source and target-data-root as well, and --hparam-json-file=/gs/hs0/tgh-19IAA/ecooper/data/vctk_hpf_sv56_preprocess_30db/target/hparams.json in scripts folder.Waiting for your letter.

Hi, the dataset in .tfrecord format can be found at the dropbox link in the readme: https://www.dropbox.com/home/multi-speaker-tacotron-data under "data". Extract source.zip and target.zip to your own location, and then update those paths to your locations.

I can't access this webpage. Can you send it to my email?thank you! rogers_sun@foxmail.com

I signed in the address,but I can not see any folder in the address.Can you send the dataset to my email?Thank you!

It looks like I pasted the link in wrong in my comment above, sorry about that -- can you access this one?

https://www.dropbox.com/sh/rq4lebus0n8tmso/AACldbmKDPRN9YiXrRROjtTSa?dl=0

You should see the folders like in this screenshot below, and you should be able to download the entire dataset using the "Download" link in the upper right:

Screen Shot 2020-08-18 at 14 41 33