Kapre

Keras Audio Preprocessors - compute STFT, ISTFT, Melspectrogram, and others on GPU real-time.

Tested on Python 3.9+ with TensorFlow 2.16-2.20, with type hints for better development experience

Why Kapre?

vs. Pre-computation

• You can optimize DSP parameters
• Your model deployment becomes much simpler and consistent.
• Your code and model has less dependencies

vs. Your own implementation

• Quick and easy!
• Consistent with 1D/2D tensorflow batch shapes
• Data format agnostic (channels_first and channels_last)
• Less error prone - Kapre layers are tested against Librosa (stft, decibel, etc) - which is (trust me) trickier than you think.
• Kapre layers have some extended APIs from the default tf.signals implementation such as..
  • A perfectly invertible STFT and InverseSTFT pair
  • Mel-spectrogram with more options
• Reproducibility - Kapre is available on pip with versioning

Workflow with Kapre

1. Preprocess your audio dataset. Resample the audio to the right sampling rate and store the audio signals (waveforms).
2. In your ML model, add Kapre layer e.g. kapre.time_frequency.STFT() as the first layer of the model.
3. The data loader simply loads audio signals and feed them into the model
4. In your hyperparameter search, include DSP parameters like n_fft to boost the performance.
5. When deploying the final model, all you need to remember is the sampling rate of the signal. No dependency or preprocessing!

Installation

pip install kapre

Development

Kapre includes comprehensive type hints for better IDE support and development experience.

Type Checking

Run type checking with our included script:

python scripts/check_types.py

Or use your preferred type checker:

# With mypy
pip install mypy
mypy kapre/

# With pyright
pip install pyright
pyright kapre/

Development Setup

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest tests/

# Run type checking
python scripts/check_types.py

# Format code
black kapre/ tests/

# Lint code
flake8 kapre/ tests/

API Documentation

Please refer to Kapre API Documentation at https://kapre.readthedocs.io

One-shot example

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Input, Conv2D, BatchNormalization, ReLU, GlobalAveragePooling2D, Dense, Softmax
from kapre import STFT, Magnitude, MagnitudeToDecibel
from kapre.composed import get_melspectrogram_layer, get_log_frequency_spectrogram_layer

# 6 channels (!), maybe 1-sec audio signal, for an example.
input_shape = (44100, 6)
sr = 44100
model = Sequential()
model.add(Input(shape=input_shape))
# A STFT layer
model.add(STFT(n_fft=2048, win_length=2048, hop_length=1024,
               window_name=None, pad_end=False,
               input_data_format='channels_last', output_data_format='channels_last'))
model.add(Magnitude())
model.add(MagnitudeToDecibel())  # these three layers can be replaced with get_stft_magnitude_layer()
# Alternatively, you may want to use a melspectrogram layer
# melgram_layer = get_melspectrogram_layer()
# or log-frequency layer
# log_stft_layer = get_log_frequency_spectrogram_layer() 

# add more layers as you want
model.add(Conv2D(32, (3, 3), strides=(2, 2)))
model.add(BatchNormalization())
model.add(ReLU())
model.add(GlobalAveragePooling2D())
model.add(Dense(10))
model.add(Softmax())

# Compile the model
model.compile('adam', 'categorical_crossentropy') # if single-label classification

# train it with raw audio sample inputs
# for example, you may have functions that load your data as below.
x = load_x() # e.g., x.shape = (10000, 44100, 6)
y = load_y() # e.g., y.shape = (10000, 10) if it's 10-class classification
# then..
model.fit(x, y)
# Done!

• See the Jupyter notebook at the example folder

TFLite compatibility

The STFT layer is not TFLite compatible (due to tf.signal.stft). To create a TFLite compatible model, first train using the normal kapre layers then create a new model replacing STFT and Magnitude with STFTTflite, MagnitudeTflite. TFLite compatible layers are restricted to a batch size of 1 which prevents use of them during training.

# assumes you have run the one-shot example above.
from kapre import STFTTflite, MagnitudeTflite
model_tflite = Sequential()
model_tflite.add(Input(shape=input_shape))

model_tflite.add(STFTTflite(n_fft=2048, win_length=2048, hop_length=1024,
               window_name=None, pad_end=False,
               input_data_format='channels_last', output_data_format='channels_last'))
model_tflite.add(MagnitudeTflite())
model_tflite.add(MagnitudeToDecibel())  
model_tflite.add(Conv2D(32, (3, 3), strides=(2, 2)))
model_tflite.add(BatchNormalization())
model_tflite.add(ReLU())
model_tflite.add(GlobalAveragePooling2D())
model_tflite.add(Dense(10))
model_tflite.add(Softmax())

# load the trained weights into the tflite compatible model.
model_tflite.set_weights(model.get_weights())

Citation

Please cite this paper if you use Kapre for your work.

@inproceedings{choi2017kapre,
  title={Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras},
  author={Choi, Keunwoo and Joo, Deokjin and Kim, Juho},
  booktitle={Machine Learning for Music Discovery Workshop at 34th International Conference on Machine Learning},
  year={2017},
  organization={ICML}
}