SashaBurashnikova

Or maybe you could show some other possibilities to generate output with an arbitrary length? I found in the text of paper that at inference step we could generate output...

Thank you for the answer, but what to do if i want to generate the output with the same length as was my input file? For ex. i take as...

I mean my question is how to define the length of the sequence that will be generated? Thank you in advance!

Thank you!I've tried to do what you suggest to change max_bars and dec_seqlen in the config and On line 284, generate.py, set max_input_len=1024, but still have the same error: [FATAL]...

Hello, I'm very sorry for disturbing you again but am i correctly understand that you will correct the config that it would be possible to define the length of sequence...

Hello, Thank you! Am i correctly understand you the i could change these parameters of config for generation part: max_bars, dec_seqlen, max_input_dec_seqlen - to change the maximum possible length of...

Sorry, maybe i don't exactly understand what do you mean, Because I see on your demos that you generated full song with modifications and the generated length for both is...

Hello again, Sorry, i found the solution for the previous problem. It was a typo in the script - estimator_spec_util.py. It should be changed tf.tpu.estimator on tf.estimator.tpu But after that...

Hello, To run on gpu in estimator_spec_util.py i changed: 1. optimizer='Adam' 2. tf.tpu.estimator.TPUEstimatorSpec -> tf.estimator.EstimatorSpec But in this way i could run only on one gpu. Do you know how...

Hello, Thank you, i solved the problem with soundfile library, the problem was in the uninstalled libsndfile1 package, that could be added to workers by changing setup.py file as was...