Development points
- Flask API server
- Variation of the model input
- v1.3: MIDITokenizerV2 and new MidiVisualizer
- v1.2 : Optimise the tokenizer and dataset. The dataset was filtered by MIDITokenizer.check_quality. Using the higher quality dataset to train the model, the performance of the model is significantly improved.
projectlosangeles/Los-Angeles-MIDI-Dataset
- install pytorch(recommend pytorch>=2.0)
- install fluidsynth>=2.0.0
pip install -r requirements.txt
python app.py
python train.py
@misc{skytnt2024midimodel,
author = {SkyTNT},
title = {Midi Model: Midi event transformer for symbolic music generation},
year = {2024},
howpublished = {\url{https://github.com/SkyTNT/midi-model}},
}