icassp2021-emotion-tts
icassp2021-emotion-tts copied to clipboard
What is `atten_weights_ph`?
In file modules/attention.py
line 434-435
if atten_weights_ph is not None: # used for emotional gst tts inference
atten_weights = atten_weights_ph
When I run inference, it stucks at this tensor. I cannot find any refer to this
Thank you for your quesstion.
When training, the attention weights of gst tokens is computed by the prosody embedding of the reference utterance(i.e. the input utterance).
When synthesizing, the attention weights is passed by this argument: atten_weights_ph
(means attention weigths placeholder
), which is computed offline by averaging attention weights of the top-K utterances of each emotion.