src.embeddings.vae
==================

.. py:module:: src.embeddings.vae


Attributes
----------

.. autoapisummary::

   src.embeddings.vae.logger


Classes
-------

.. autoapisummary::

   src.embeddings.vae.VAEEmbedding


Functions
---------

.. autoapisummary::

   src.embeddings.vae._compute_spectrogram


Module Contents
---------------

.. py:data:: logger

.. py:class:: VAEEmbedding(dataset_name: str, clip_duration: float = 3.0, model_path: str or pathlib.Path or None = None, sampling_rate: int or None = None, learning_rate=0.05, batch_size=16, epochs=10, latent_dim=128, beta_kl=1, kw_spectrograms: dict or None = None)

   Bases: :py:obj:`embeddings.BaseEmbedding`


   VAEEmbedding class for computing spectrograms from audio data and fitting a Variational Autoencoder (VAE).

   This class extends BaseEmbedding and provides functionality for computing spectrograms
   and training a VAE on those spectrograms.

   Attributes:
   -----------
   model_path : str
       Path where the VAE model will be saved or loaded.
   data : pd.DataFrame or None
       DataFrame holding the computed spectrograms.
   vae : tensorflow.keras.Model
       The VAE model used to fit the spectrogram data.

   Methods:
   --------
   load_model():
       Loads a pre-trained VAE model if available.

   process(dataset_name: str, extension: str = '.wav', sampling_rate: int = 48000, **kwargs):
       Processes the audio dataset by computing spectrograms and fitting a VAE.



   .. py:attribute:: learning_rate


   .. py:attribute:: epochs


   .. py:attribute:: batch_size


   .. py:attribute:: latent_dim


   .. py:attribute:: beta_kl


   .. py:attribute:: kw_spectrograms


   .. py:attribute:: model
      :value: None



   .. py:attribute:: spectrograms
      :value: None



   .. py:method:: compute_spectrograms()


   .. py:method:: load_model()


   .. py:method:: train_model()


   .. py:method:: process()


.. py:function:: _compute_spectrogram(audio: numpy.array, sample_rate: int, resolution: float, overlap: float, freq_min: float, freq_max: float or None, n_freqs: int, **kwargs)