skytnt
/

midi-model

music generation

midi generation

Model card Files Files and versions

Model Card for midi-model

Midi event transformer for music generation

Model Updates

tv2o-medium model: MidiTokenizerV2. skytnt/midi-model-tv2o-medium
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.

Model Details

Model Description

Developed by: SkyTNT
Model type: Transformer
License: apache-2.0

Model Sources

Repository: https://github.com/SkyTNT/midi-model
Demo: https://huggingface.co/spaces/skytnt/midi-composer

Training Details

Training Data

projectlosangeles/Los-Angeles-MIDI-Dataset

Training Hyperparameters

basemodel: v1.1
lr: 1e-4
weight-decay: 0.01
batch: 2x2x2
fp16 mixed precision

Loss

val loss: 0.238

Files

model.ckpt: latest model checkpoint
soundfont.sf2: soundfont file, i put it here for convenient downloading , source
onnx/*.onnx: onnx format model

Downloads last month: 190

Safetensors

Model size

0.2B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for skytnt/midi-model

Finetunes

Quantizations

Dataset used to train skytnt/midi-model

Spaces using skytnt/midi-model 25