“One very valid reason for existing is that we are here to create. What AI cannot do is perhaps a potential reason for why we exist. One such direction is that we create. We invent things. We celebrate creation.”
The M-AILABS Speech Dataset is the first large dataset that we are providing free-of-charge, freely usable as training data for speech recognition and speech synthesis. Most of the data is based on LibriVox and Project Gutenberg. The training data consist of nearly thousand hours of audio and the text-files in prepared format. A transcription is provided[…]
One of the major tasks in training machine learning (if not the major-task) is preparing the training data. This is a tedious task that requires people who like repetitive work. Though it is tedious, it is (in our opinion) even more important than knowing which model to use, what software to write to train the system.
The last few days, we were training our Keras2-based WaveNet on samples from Chopin. The samples are just two pieces by Frederic Chopin, recorded very long ago and thus out-of-copyright. We still have a long way to go (and also figure out why we had a dead-lock during Multi-GPU-training). Because of that deadlock, we are[…]
At Munich Artificial Intelligence Laboratories (M-AILABS), we experiment with a lot of technologies and methods. We also look for novel ways of doing things in the area of ML & AI.
One of my personal dreams is to have an AI-based solution that can “compose” music. And of course, it has to be music like the great Ludwig van. So, we started looking for some papers.