MelSpectrogram

A preprocessing layer to convert raw audio signals to Mel spectrograms.

Abstract Signature:

MelSpectrogram(fft_length: int = 2048, sequence_stride: int = 512, num_mel_bins: int = 128, sampling_rate: int = 16000)

PyTorchKerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torchaudio.transforms.MelSpectrogram

Strategy: Direct Mapping

Official Docs ↗

Keras

API: keras.layers.MelSpectrogram

Strategy: Direct Mapping

Official Docs ↗

TensorFlow

API: tf.keras.layers.MelSpectrogram

Strategy: Direct Mapping

Official Docs ↗

Apple MLX

API: —

Strategy: Custom / Partial

Flax NNX

API: —

Strategy: Custom / Partial

PaxML / Praxis

API: —

Strategy: Custom / Partial