I’m wondering how I can use cGPT in a particular usecase and if so how can I go about feeding training data to it?
Whati am trying to accomplish: I want to be able to supply cGPT with a music file (.ogg or .mp3) and get an accuracy of .001 BPM as to what the BPM of a song is. Huge bonus points if it can also print out at which second (down to .001 sec) where a BPM would change in a song.
DJ software is extremely inaccurate. It’s good for a rough estimate, but it can be wildly wrong at times.
In my experience, at least for digitally produced music that has a constant tempo and a 4/4 measure, the DJ software will get it perfectly right more than 95% of the time. In those few cases where it fails, it seems to me that it’s most often caused by bad/weird/artsy/interesting mixing choices in the production, where e.g. the bass notes are more preminent than the kick drum, confusing the algorithm with an irregular kind of waveform. I guess manually EQ’ing the audio file itself to make the drums more prominent than the bass notes, then letting the software analyse the BPM once again, could be a solution. For non-quantized recordings with musically organic tempo changes, it’s definitely a much different story…