leonardog27

we are making prior level 2 training using Colab. We have a group on discord called What kind of special set up we need to do to dataset for lyrics...

There is now a continuation mode with partial progressive save in Gdrive. Please enter the discord group Jukebox Fans and the improved colab notebook is pinned on the coding discussion...

 Good morning friends! Please help us to review about this code we are using to train prior level 2. The checkpoint tar file does not grow size more than...

For Prior Level 2 training? What is the recommended dataset time duration we should use? What are the amount of training steps we must train? It is needed remove voices...

>  > Good morning friends! Please help us to review about this code we are using to train prior level 2. > The checkpoint tar file does not grow...

> I'm glad it worked! In my script, I don't have to change the `sample_length_in_seconds`, so I wonder what's different here… 🤔 > > Ah, okay -- I just actually...

I am going to do 3 samples 5B Model Symphonic of the Imperial March, 8 minutes each. Using upsampling by parts (4 parts)  🎼🤖👨‍💻 Thank you very much.

top_prior_raw_to_tokens = 32 hps.sample_length = zs[2].shape[1] * top_prior_raw_to_tokens zs = upsample(zs_part4, labels, sampling_kwargs, [*upsamplers, top_prior], hps) The following error message appear at the moment to upsample PART 4, please help...

 Assertion Error appears on this try... :(

Plan B running as follows: