Spaces:
Sleeping
Sleeping
Inversynth Fork
AMP Team
Launch instructions :
Optional: outputing your own config file for your VST
python -m generators.vst_generator generate
1. Dataset Creation based on config profile
python -m generators.vst_generator run --config "your_config_path.json"
2. Model training
python -m generators.spectrogram_cnn --epoch "your_epoch_number" --model C6XL
| Parameter | Default | Description |
|---|---|---|
--num_examples |
2000 |
Number of examples to create |
--name |
InverSynth |
Naming convention for datasets |
--dataset_directory |
test_datasets |
Directory for datasets |
--wavefile_directory |
test_waves |
Directory to for wave files. Naming convention applied automatically |
--length |
1.0 |
Length of each sample in seconds |
--sample_rate |
16384 |
Sample rate (Samples/second) |
--sampling_method |
random |
Method to use for generating examples. Currently only random, but may include whole space later |
| Optional | ||
--regenerate_samples |
Regenerate the set of points to explore if it exists (will also force regenerating audio) |
|
--regenerate_audio |
Regenerate audio files if they exist | |
--normalise |
Apply audio normalization |
This module generates a dataset attempting to recreate the dataset generation
as defined in the paper
Selecting an architecture:
C1,C2,C3,C4,C5,C6,C6XL