Hands-On Music Generation with Magenta by Alexandre DuBreuil

Author:Alexandre DuBreuil [Alexandre DuBreuil]
Language: eng
Format: epub
Tags: COM037000 - COMPUTERS / Machine Theory, COM051360 - COMPUTERS / Programming Languages / Python, COM044000 - COMPUTERS / Neural Networks
Publisher: Packt
Published: 2020-01-31T07:07:44+00:00

Choosing the acoustic model

Magenta provides two pre-trained GANSynth models: acoustic_only, where the model was trained only on acoustic instruments, and all_instruments, where the model was trained on the whole NSynth dataset (see the previous section, The NSynth dataset, for more information on the dataset).

We're going to use the acoustic_only dataset for our example since the resulting audio track of a Bach score will sound more natural in terms of instrument choices. If you want to produce a wider generation, use the all_instruments model.

You can follow this example in the chapter_05_example_02.py file in the source code of this chapter. There are more comments and content in the source code, so you should go check it out.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.