omnizart patch-cnn¶

Lists the detailed available options of each sub-commands.

transcribe¶

omnizart patch-cnn transcribe¶

Transcribe a single audio and output CSV and audio file.

The transcribed F0 contour will be stored in the <filename>_f0.csv file, where filename is the input file name. Also there will be another rendered audio file (with postfix <filename>_trans.wav) of the pitch contour for quick validation.

Supported modes are: Melody

omnizart patch-cnn transcribe [OPTIONS] INPUT_AUDIO

Options

-m, --model-path <model_path>¶: Path to the pre-trained model or the supported transcription mode.

-o, --output <output>¶

Path to output the prediction file (could be MIDI, CSV, …, etc.)

Default: ./

Arguments

INPUT_AUDIO¶: Required argument

generate-feature¶

omnizart patch-cnn generate-feature¶

Pre-process the dataset for training.

Supported datasets are:

* MIR-1K

omnizart patch-cnn generate-feature [OPTIONS]

Options

-d, --dataset-path <dataset_path>¶: Required Path to the downloaded dataset

-o, --output-path <output_path>¶: Path for saving the extracted feature. Default to the folder under the dataset.

-n, --num-threads <num_threads>¶

Number of threads used for parallel feature extraction.

Default: 4

train-model¶

omnizart patch-cnn train-model¶

Train a new model or continue to train on a pre-trained model

omnizart patch-cnn train-model [OPTIONS]

Options

-d, --feature-path <feature_path>¶: Required Path to the folder of extracted feature

-m, --model-name <model_name>¶: Name for the output model (can be a path)

-i, --input-model <input_model>¶: If given, the training will continue to fine-tune the pre-trained model.

-e, --epochs <epochs>¶: Number of training epochs

-s, --steps <steps>¶: Number of training steps of each epoch

-vs, --val-steps <val_steps>¶: Number of validation steps of each epoch

-b, --batch-size <batch_size>¶: Batch size of each training step

-vb, --val-batch-size <val_batch_size>¶: Batch size of each validation step

--early-stop <early_stop>¶: Stop the training if validation accuracy does not improve over the given number of epochs.