If you have trouble using any notebooks, make sure you use the correct notebooks, which are linked in the #notebooks channel, as those notebooks are the most up-to-date ones.

Why are you trying to use an outdated version of the notebook?

I found it in a video regarding the subject. I really should've checked here first

I concur

Now that I've tried the more updated one, it's saying that list.txt isn't a directory even though it is

and, no. it's not a capital I in the file name

That's odd. I could've sworn I'd changed the required .txt file to be

transcript.txt

instead of

list.txt

.

hmm... I'll rename it to transcript.txt

That's the solution

same problem

Oh. Hmm.

Can you send the .txt file here?

Ok. I'll do that tomorrow. It's getting late in my timezone

I mean on Microsoft Office

Even on the notebook I usually use to train, it gives me this error on import libraries and define functions: /content/tacotron2/text/__init__.py:74: SyntaxWarning: "is not" with a literal. Did you mean "!="? return s in _symbol_to_id and s is not '_' and s is not '~' /content/tacotron2/text/__init__.py:74: SyntaxWarning: "is not" with a literal. Did you mean "!="? return s in _symbol_to_id and s is not '_' and s is not '~' --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 396 397 # ---- DEFAULT PARAMETERS DEFINED HERE ---- --> 398 hparams = create_hparams() 399 model_filename = 'current_model' 400 hparams.training_files = "filelists/clipper_train_filelist.txt" /content/tacotron2/hparams.py in create_hparams(hparams_string, verbose) 6 """Create model hyperparameters. Parse nondefault from given string.""" 7 ----> 8 hparams = tf.contrib.training.HParams( 9 ################################ 10 # Experiment Parameters # AttributeError: module 'tensorflow' has no attribute 'contrib'

Can you send me the link to that notebook?

Sure, here you go: https://colab.research.google.com/drive/1uObIlubY9MDHpBuzot_jjWEVZSs2sgI9

when i run the synthesis notebook, i got these problem

I can probably guess that I didn't set up the transcript properly

It's organized like this

wavs/1|Sentence 1.
wavs/2|Sentence 2.
wavs/3|Sentence 3.

Is this method outdated?

hold on, is the sentences just "Sentence (number)"? because I dont think it works like that

That's placeholder data. Put the words said on the audio file in its place

I think

working on training a new model, but i continue to get the cuda memory error. the gpu in the colab is a t4. tried 16 originally, cuda error. moved back to 8, still cuda error. what do i do?

What gpu do you use?

the one i was given in the colab was a tesla t4, my actual computer is an intel uhd

Oh that's it. Integrated graphics suck

colab doesn't use ANY of your components

it's all google's stuff

exactly, ive been able to do this before with no problems even related to the memory