dc_tts
dc_tts copied to clipboard
Kyubyong
I struggled to get anything but errors for the longest. Here's what finally got me able to run 'synthesize.py'
Starting with the downloads listed on main page: LJ Dataset: https://keithito.com/LJ-Speech-Dataset/ needs to be unpacked and put somewhere. Adjust 'data = ' in hyperparameters.py to point to it. ----> Change the name of the .csv file in that folder to 'transcript.csv'. I can't remember now what it was called, but everything will fail unless it's named transcript.csv.
Pretrained models for LJ : https://www.dropbox.com/s/1oyipstjxh2n5wo/LJ_logdir.tar?dl=0 make a directory named 'logdir' in dc_tts. Untar both the LJ01-1 and LJ01-2 folders in there. Again, everything bombs without them being located there.
finally, mkdir samples in dc_tts, or it'll complain about nowhere to write.
If you get obscure errors like "TypeError: new() got an unexpected keyword argument 'file'", you're in luck because I know what to do. Your 'protobuf' python library is out of date. Turned out for me a rogue older version was hiding out in ~/.local/lib/python2.7/site-packages/. Pip didnt seem to mind or notice when I did a million varieties of attempting to uninstall/reinstall. Finally, I rm -rf -ed that mother and then did a sudo -H pip install --upgrade protobuf. You need to make sure your version is greater than 3.something-or-other or again, no dice.
... python synthesize.py at this point runs to completion. It produces 20 files, I assume meant to match the 'harvard_sentences.txt' file, all garbled static or silence only, but it indeed completed. That's a start.
Wait wait! No way! Its now working! At some point in all the chaos I ran 'prepro.py' which created folders mels/ and mags/. I deleted the both of these and ran synthesize.py again, and ! Amazing. My 20hrs of fumbling in the dark paid off. Thank you for sharing this with us lesser minds @ Kyubyong
further notes on this:
You can adjust max_N and max_T in hyperparams down to 60 and make inference (for short phrases) nearly 20x+ faster. I can't tell any difference in quality of the output. To begin with, the same phrase that now takes 14 seconds would take over two minutes. Here's some samples.
sample.zip
I made a little wrapper so one can simply go ./wrapper.py "phrase to say" and it'll speak it as soon as it's done, along with saving file to backups/
https://gist.github.com/rocket-pig/393b752fb0c5bb43e03ff5b6d1c1cf74
Now maybe i can daemonize it and just RPC/curl or something to have a functional TTS system. Thank you so much for sharing this. !
Very helpful thanks! I couldn't make the training work, I suspect due to tensorflow 1.8? But using your pretrained models, syntehsizing works great! Did you proceed beyond 700k? Would it keep improving?
ValueError: Can't load save_path when it is None. WhileI synthesizing i got this error. please help me
ValueError: Can't load save_path when it is None. WhileI synthesizing i got this error. please help me
Same
Make sure that you should have log1 and log2 folder in logdir folder.. Inside those log1 and log2 folder it should have models.
Fathima Msc Scholar Department of Computational biology and BioInformatics UoK
On Fri, 24 Apr, 2020, 2:18 PM nwlutz <[email protected] wrote:
ValueError: Can't load save_path when it is None. WhileI synthesizing i got this error. please help me
Same
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/Kyubyong/dc_tts/issues/14#issuecomment-618887559, or unsubscribe https://github.com/notifications/unsubscribe-auth/AONUIFZWRDTYVRG6QEFGOUTROFG4LANCNFSM4EXJ36TA .