tar -xzf piano_transcription.tar.gz -C piano_transcription
source piano_transcription/bin/activate

Download the MAESTRO dataset and place it in a dataset folder within the piano_transcription directory. Mozart is already included.

Modify the Config File：

Paths: Update root, ckpt_path, and configs_path to absolute paths on your system (e.g., replace /home/zheqid/workspace/ with your local directory).
Codec Vocab Size: Set vocab_size to match your audio codec (e.g., 65536 for trancodec_fsq).
Model Size: Adjust n_layer, n_head, and n_embd to scale the model (e.g., increase for a larger model).
Hardware: Modify device and batch_size_per_device based on your GPU setup.

Then train as follow :

python train.py --config /home/zheqid/workspace/musictokenizer/configs/mozart.yaml

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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