I'm looking to train a word2vec 2.0 model from scratch, but I am a bit new to the field. Crucially, I would like to train it using a large dataset of non-human speech (i.e. cetacean sounds) in order to capture the underlying structure.
Once the pre-training is performed, is it possible to visualize the embeddings the model creates, in a similar way to how latent features are visualized in image processing when using e.g. CNNs? Or are the representations too abstract to be mapped to a spectrogram?
What I would like to do is to see what features the network is learning as the units of speech.
Thanks in advance for the help!