Tim Braun

Update on this one: I did a little research and it seems that the audio features in `data_load.py` are calculated over and over again. As a first hack I had...

@zuoxiang95 As my dataset is very small (~12 GB of features) I managed to put it all to RAM and that improved training speed as well as GPU usage EDIT:...

The beauty of end to end speech synthesis is that you feed in pairs of audio and transcriptions and you're good to go. You'll need a whole lot of expertise...

If you didn't mess with the code - it should continue training from the latest saved checkpoint.

As far as I remember, epochs aren't saved with the model. It's just a range that the code iterates over. You may want to check with `tensorboard` and see if...

Guys, I've run some training for around 32k global steps using @ggsonic s latest commit. I used a german dataset (pavoque in case someone is interested) and I've got some...

No not yet. I definitely plan to do things like that but my first goal is or was to prove that it's worth spending all that time :D I'll keep...

Sorry guys, I totally forgot to answer ... weekend. I use a really small corpus. Around 5.3 hours of utterances. It seems to be enough to generate random new sentences....

I didn't have much luck with the new features introduced during the last commits. I do get the best results with 7ed2f209233c307b968c7080bc36fda3a70f6707 by ggsonic and the loss curves are similar...

As far as I understand what the paper says they're predicting frames `1..r` in at once. If that's correct then the current state of the `reduce_frames` method is not correct....