Reputation: 57
I am trying to install this Python application (https://github.com/NVIDIA/tacotron2/) and do not understand a required installation step.
I think that the instructions are asking me to specify a path, but I don't know how to do this.
Update .wav
paths:
$ sed -i -- 's,DUMMY,ljs_dataset_folder/wavs,g' filelists/*.txt
After updating the .wav paths, the user is then instructed to:
Install PyTorch 1.0 Install python requirements or build docker image
Install python requirements: pip install -r requirements.txt
But I am still stumped by the instruction to update the .wav
path.
Upvotes: 0
Views: 314
Reputation:
What the sed
command does is:
.txt
files in the filelists
directory.DUMMY
with ljs_dataset_folder/wavs
.txt
file.That's it.
Upvotes: 1
Reputation: 11
the steps are self-explanatory Update .wav paths:
sed -i -- 's,DUMMY,ljs_dataset_folder/wavs,g' filelists/*.txt
SED command in UNIX is stands for stream editor and it can perform lot’s of function on file like, searching, find and replace, insertion or deletion. Though most common use of SED command in UNIX is for substitution or for find and replace. By using SED you can edit files even without opening it, which is much quicker way to find and replace something in file, than first opening that file in VI Editor and then changing it. OR
Alternatively, set load_mel_from_disk=True in hparams.py and update mel-spectrogram paths
https://github.com/NVIDIA/tacotron2/blob/master/hparams.py line26th
You can download the The LJ Speech Dataset from https://keithito.com/LJ-Speech-Dataset/ and put this into a folder named ljs_dataset_folder or anything of your choice.
Upvotes: 0